nhu/kernel_a52xq
Watch
1
Fork
You've already forked kernel_a52xq
 0
mirror of https://github.com/a52xq-dev/kernel.git synced 2026-10-18 21:58:11 +07:00
Code Issues Projects Releases Wiki Activity

Merge remote-tracking branch 'aosp/upstream-f2fs-stable-linux-4.19.y' into android-4.19

Browse source 
* aosp/upstream-f2fs-stable-linux-4.19.y:
  f2fs: add a condition to detect overflow in f2fs_ioc_gc_range()
  f2fs: fix to add missing F2FS_IO_ALIGNED() condition
  f2fs: fix to fallback to buffered IO in IO aligned mode
  f2fs: fix to handle error path correctly in f2fs_map_blocks
  f2fs: fix extent corrupotion during directIO in LFS mode
  f2fs: check all the data segments against all node ones
  f2fs: Add a small clarification to CONFIG_FS_F2FS_FS_SECURITY
  f2fs: fix inode rwsem regression
  f2fs: fix to avoid accessing uninitialized field of inode page in is_alive()
  f2fs: avoid infinite GC loop due to stale atomic files
  f2fs: Fix indefinite loop in f2fs_gc()
  f2fs: convert inline_data in prior to i_size_write
  f2fs: fix error path of f2fs_convert_inline_page()
  f2fs: add missing documents of reserve_root/resuid/resgid
  f2fs: fix flushing node pages when checkpoint is disabled
  f2fs: enhance f2fs_is_checkpoint_ready()'s readability
  f2fs: clean up __bio_alloc()'s parameter
  f2fs: fix wrong error injection path in inc_valid_block_count()
  f2fs: fix to writeout dirty inode during node flush
  f2fs: optimize case-insensitive lookups
  f2fs: introduce f2fs_match_name() for cleanup
  f2fs: Fix indefinite loop in f2fs_gc()
  f2fs: allocate memory in batch in build_sit_info()
  f2fs: support FS_IOC_{GET,SET}FSLABEL
  f2fs: fix to avoid data corruption by forbidding SSR overwrite
  f2fs: Fix build error while CONFIG_NLS=m
  Revert "f2fs: avoid out-of-range memory access"
  f2fs: cleanup the code in build_sit_entries.
  f2fs: fix wrong available node count calculation
  f2fs: remove duplicate code in f2fs_file_write_iter
  f2fs: fix to migrate blocks correctly during defragment
  f2fs: use wrapped f2fs_cp_error()
  f2fs: fix to use more generic EOPNOTSUPP
  f2fs: use wrapped IS_SWAPFILE()
  f2fs: Support case-insensitive file name lookups
  f2fs: include charset encoding information in the superblock
  fs: Reserve flag for casefolding
  f2fs: fix to avoid call kvfree under spinlock
  fs: f2fs: Remove unnecessary checks of SM_I(sbi) in update_general_status()
  f2fs: disallow direct IO in atomic write
  f2fs: fix to handle quota_{on,off} correctly
  f2fs: fix to detect cp error in f2fs_setxattr()
  f2fs: fix to spread f2fs_is_checkpoint_ready()
  f2fs: support fiemap() for directory inode
  f2fs: fix to avoid discard command leak
  f2fs: fix to avoid tagging SBI_QUOTA_NEED_REPAIR incorrectly
  f2fs: fix to drop meta/node pages during umount
  f2fs: disallow switching io_bits option during remount
  f2fs: fix panic of IO alignment feature
  f2fs: introduce {page,io}_is_mergeable() for readability
  f2fs: fix livelock in swapfile writes
  f2fs: add fs-verity support
  ext4: update on-disk format documentation for fs-verity
  ext4: add fs-verity read support
  ext4: add basic fs-verity support
  fs-verity: support builtin file signatures
  fs-verity: add SHA-512 support
  fs-verity: implement FS_IOC_MEASURE_VERITY ioctl
  fs-verity: implement FS_IOC_ENABLE_VERITY ioctl
  fs-verity: add data verification hooks for ->readpages()
  fs-verity: add the hook for file ->setattr()
  fs-verity: add the hook for file ->open()
  fs-verity: add inode and superblock fields
  fs-verity: add Kconfig and the helper functions for hashing
  fs: uapi: define verity bit for FS_IOC_GETFLAGS
  fs-verity: add UAPI header
  fs-verity: add MAINTAINERS file entry
  fs-verity: add a documentation file
  ext4: fix kernel oops caused by spurious casefold flag
  ext4: fix coverity warning on error path of filename setup
  ext4: optimize case-insensitive lookups
  ext4: fix dcache lookup of !casefolded directories
  unicode: update to Unicode 12.1.0 final
  unicode: add missing check for an error return from utf8lookup()
  ext4: export /sys/fs/ext4/feature/casefold if Unicode support is present
  unicode: refactor the rule for regenerating utf8data.h
  ext4: Support case-insensitive file name lookups
  ext4: include charset encoding information in the superblock
  unicode: update unicode database unicode version 12.1.0
  unicode: introduce test module for normalized utf8 implementation
  unicode: implement higher level API for string handling
  unicode: reduce the size of utf8data[]
  unicode: introduce code for UTF-8 normalization
  unicode: introduce UTF-8 character database
  ext4 crypto: fix to check feature status before get policy
  fscrypt: document the new ioctls and policy version
  ubifs: wire up new fscrypt ioctls
  f2fs: wire up new fscrypt ioctls
  ext4: wire up new fscrypt ioctls
  fscrypt: require that key be added when setting a v2 encryption policy
  fscrypt: add FS_IOC_REMOVE_ENCRYPTION_KEY_ALL_USERS ioctl
  fscrypt: allow unprivileged users to add/remove keys for v2 policies
  fscrypt: v2 encryption policy support
  fscrypt: add an HKDF-SHA512 implementation
  fscrypt: add FS_IOC_GET_ENCRYPTION_KEY_STATUS ioctl
  fscrypt: add FS_IOC_REMOVE_ENCRYPTION_KEY ioctl
  fscrypt: add FS_IOC_ADD_ENCRYPTION_KEY ioctl
  fscrypt: rename keyinfo.c to keysetup.c
  fscrypt: move v1 policy key setup to keysetup_v1.c
  fscrypt: refactor key setup code in preparation for v2 policies
  fscrypt: rename fscrypt_master_key to fscrypt_direct_key
  fscrypt: add ->ci_inode to fscrypt_info
  fscrypt: use FSCRYPT_* definitions, not FS_*
  fscrypt: use FSCRYPT_ prefix for uapi constants
  fs, fscrypt: move uapi definitions to new header <linux/fscrypt.h>
  fscrypt: use ENOPKG when crypto API support missing
  fscrypt: improve warnings for missing crypto API support
  fscrypt: improve warning messages for unsupported encryption contexts
  fscrypt: make fscrypt_msg() take inode instead of super_block
  fscrypt: clean up base64 encoding/decoding
  fscrypt: remove loadable module related code

 Conflicts:
	fs/ext4/ioctl.c
	fs/ext4/readpage.c

Bug: 141329812
Change-Id: I2e10c22a7c52982d073ac6897cc8aa4d5a811a38
Signed-off-by: Jaegeuk Kim <jaegeuk@google.com>
This commit is contained in:
Jaegeuk Kim 2019-10-07 13:27:18 -07:00
commit c2ad33f029
90 changed files with 18137 additions and 1292 deletions
Download patch file Download diff file Expand all files Collapse all files

7
Documentation/ABI/testing/sysfs-fs-f2fs
View file

@ -251,3 +251,10 @@ Description:
If checkpoint=disable, it displays the number of blocks that are unusable.
If checkpoint=enable it displays the enumber of blocks that would be unusable
if checkpoint=disable were to be set.
What: /sys/fs/f2fs/<disk>/encoding
Date July 2019
Contact: "Daniel Rosenberg" <drosen@google.com>
Description:
Displays name and version of the encoding set for the filesystem.
If no encoding is set, displays (none)

2
Documentation/dontdiff
View file

@ -177,6 +177,7 @@ mkprep
mkregtable
mktables
mktree
mkutf8data
modpost
modules.builtin
modules.order
@ -255,6 +256,7 @@ vsyscall_32.lds
wanxlfw.inc
uImage
unifdef
utf8data.h
wakeup.bin
wakeup.elf
wakeup.lds

1
Documentation/filesystems/ext4/ondisk/overview.rst
View file

@ -24,3 +24,4 @@ order.
.. include:: bigalloc.rst
.. include:: inlinedata.rst
.. include:: eainode.rst
.. include:: verity.rst

41
Documentation/filesystems/ext4/verity.rst Normal file
View file

@ -0,0 +1,41 @@
.. SPDX-License-Identifier: GPL-2.0
Verity files
------------
ext4 supports fs-verity, which is a filesystem feature that provides
Merkle tree based hashing for individual readonly files. Most of
fs-verity is common to all filesystems that support it; see
:ref:`Documentation/filesystems/fsverity.rst <fsverity>` for the
fs-verity documentation. However, the on-disk layout of the verity
metadata is filesystem-specific. On ext4, the verity metadata is
stored after the end of the file data itself, in the following format:
- Zero-padding to the next 65536-byte boundary. This padding need not
actually be allocated on-disk, i.e. it may be a hole.
- The Merkle tree, as documented in
:ref:`Documentation/filesystems/fsverity.rst
<fsverity_merkle_tree>`, with the tree levels stored in order from
root to leaf, and the tree blocks within each level stored in their
natural order.
- Zero-padding to the next filesystem block boundary.
- The verity descriptor, as documented in
:ref:`Documentation/filesystems/fsverity.rst <fsverity_descriptor>`,
with optionally appended signature blob.
- Zero-padding to the next offset that is 4 bytes before a filesystem
block boundary.
- The size of the verity descriptor in bytes, as a 4-byte little
endian integer.
Verity inodes have EXT4_VERITY_FL set, and they must use extents, i.e.
EXT4_EXTENTS_FL must be set and EXT4_INLINE_DATA_FL must be clear.
They can have EXT4_ENCRYPT_FL set, in which case the verity metadata
is encrypted as well as the data itself.
Verity files cannot have blocks allocated past the end of the verity
metadata.

8
Documentation/filesystems/f2fs.txt
View file

@ -157,6 +157,11 @@ noinline_data Disable the inline data feature, inline data feature is
enabled by default.
data_flush Enable data flushing before checkpoint in order to
persist data of regular and symlink.
reserve_root=%d Support configuring reserved space which is used for
allocation from a privileged user with specified uid or
gid, unit: 4KB, the default limit is 0.2% of user blocks.
resuid=%d The user ID which may use the reserved blocks.
resgid=%d The group ID which may use the reserved blocks.
fault_injection=%d Enable fault injection in all supported types with
specified injection rate.
fault_type=%d Support configuring fault injection type, should be
@ -413,6 +418,9 @@ Files in /sys/fs/f2fs/<devname>
that would be unusable if checkpoint=disable were
to be set.
encoding This shows the encoding used for casefolding.
If casefolding is not enabled, returns (none)
================================================================================
USAGE
================================================================================

750
Documentation/filesystems/fscrypt.rst
View file

@ -72,6 +72,9 @@ Online attacks
fscrypt (and storage encryption in general) can only provide limited
protection, if any at all, against online attacks. In detail:
Side-channel attacks
~~~~~~~~~~~~~~~~~~~~
fscrypt is only resistant to side-channel attacks, such as timing or
electromagnetic attacks, to the extent that the underlying Linux
Cryptographic API algorithms are. If a vulnerable algorithm is used,
@ -80,29 +83,90 @@ attacker to mount a side channel attack against the online system.
Side channel attacks may also be mounted against applications
consuming decrypted data.
After an encryption key has been provided, fscrypt is not designed to
hide the plaintext file contents or filenames from other users on the
same system, regardless of the visibility of the keyring key.
Instead, existing access control mechanisms such as file mode bits,
POSIX ACLs, LSMs, or mount namespaces should be used for this purpose.
Also note that as long as the encryption keys are *anywhere* in
memory, an online attacker can necessarily compromise them by mounting
a physical attack or by exploiting any kernel security vulnerability
which provides an arbitrary memory read primitive.
Unauthorized file access
~~~~~~~~~~~~~~~~~~~~~~~~
While it is ostensibly possible to "evict" keys from the system,
recently accessed encrypted files will remain accessible at least
until the filesystem is unmounted or the VFS caches are dropped, e.g.
using ``echo 2 > /proc/sys/vm/drop_caches``. Even after that, if the
RAM is compromised before being powered off, it will likely still be
possible to recover portions of the plaintext file contents, if not
some of the encryption keys as well. (Since Linux v4.12, all
in-kernel keys related to fscrypt are sanitized before being freed.
However, userspace would need to do its part as well.)
After an encryption key has been added, fscrypt does not hide the
plaintext file contents or filenames from other users on the same
system. Instead, existing access control mechanisms such as file mode
bits, POSIX ACLs, LSMs, or namespaces should be used for this purpose.
Currently, fscrypt does not prevent a user from maliciously providing
an incorrect key for another user's existing encrypted files. A
protection against this is planned.
(For the reasoning behind this, understand that while the key is
added, the confidentiality of the data, from the perspective of the
system itself, is *not* protected by the mathematical properties of
encryption but rather only by the correctness of the kernel.
Therefore, any encryption-specific access control checks would merely
be enforced by kernel *code* and therefore would be largely redundant
with the wide variety of access control mechanisms already available.)
Kernel memory compromise
~~~~~~~~~~~~~~~~~~~~~~~~
An attacker who compromises the system enough to read from arbitrary
memory, e.g. by mounting a physical attack or by exploiting a kernel
security vulnerability, can compromise all encryption keys that are
currently in use.
However, fscrypt allows encryption keys to be removed from the kernel,
which may protect them from later compromise.
In more detail, the FS_IOC_REMOVE_ENCRYPTION_KEY ioctl (or the
FS_IOC_REMOVE_ENCRYPTION_KEY_ALL_USERS ioctl) can wipe a master
encryption key from kernel memory. If it does so, it will also try to
evict all cached inodes which had been "unlocked" using the key,
thereby wiping their per-file keys and making them once again appear
"locked", i.e. in ciphertext or encrypted form.
However, these ioctls have some limitations:
- Per-file keys for in-use files will *not* be removed or wiped.
Therefore, for maximum effect, userspace should close the relevant
encrypted files and directories before removing a master key, as
well as kill any processes whose working directory is in an affected
encrypted directory.
- The kernel cannot magically wipe copies of the master key(s) that
userspace might have as well. Therefore, userspace must wipe all
copies of the master key(s) it makes as well; normally this should
be done immediately after FS_IOC_ADD_ENCRYPTION_KEY, without waiting
for FS_IOC_REMOVE_ENCRYPTION_KEY. Naturally, the same also applies
to all higher levels in the key hierarchy. Userspace should also
follow other security precautions such as mlock()ing memory
containing keys to prevent it from being swapped out.
- In general, decrypted contents and filenames in the kernel VFS
caches are freed but not wiped. Therefore, portions thereof may be
recoverable from freed memory, even after the corresponding key(s)
were wiped. To partially solve this, you can set
CONFIG_PAGE_POISONING=y in your kernel config and add page_poison=1
to your kernel command line. However, this has a performance cost.
- Secret keys might still exist in CPU registers, in crypto
accelerator hardware (if used by the crypto API to implement any of
the algorithms), or in other places not explicitly considered here.
Limitations of v1 policies
~~~~~~~~~~~~~~~~~~~~~~~~~~
v1 encryption policies have some weaknesses with respect to online
attacks:
- There is no verification that the provided master key is correct.
Therefore, a malicious user can temporarily associate the wrong key
with another user's encrypted files to which they have read-only
access. Because of filesystem caching, the wrong key will then be
used by the other user's accesses to those files, even if the other
user has the correct key in their own keyring. This violates the
meaning of "read-only access".
- A compromise of a per-file key also compromises the master key from
which it was derived.
- Non-root users cannot securely remove encryption keys.
All the above problems are fixed with v2 encryption policies. For
this reason among others, it is recommended to use v2 encryption
policies on all new encrypted directories.
Key hierarchy
=============
@ -123,11 +187,52 @@ appropriate master key. There can be any number of master keys, each
of which protects any number of directory trees on any number of
filesystems.
Userspace should generate master keys either using a cryptographically
secure random number generator, or by using a KDF (Key Derivation
Function). Note that whenever a KDF is used to "stretch" a
lower-entropy secret such as a passphrase, it is critical that a KDF
designed for this purpose be used, such as scrypt, PBKDF2, or Argon2.
Master keys must be real cryptographic keys, i.e. indistinguishable
from random bytestrings of the same length. This implies that users
**must not** directly use a password as a master key, zero-pad a
shorter key, or repeat a shorter key. Security cannot be guaranteed
if userspace makes any such error, as the cryptographic proofs and
analysis would no longer apply.
Instead, users should generate master keys either using a
cryptographically secure random number generator, or by using a KDF
(Key Derivation Function). The kernel does not do any key stretching;
therefore, if userspace derives the key from a low-entropy secret such
as a passphrase, it is critical that a KDF designed for this purpose
be used, such as scrypt, PBKDF2, or Argon2.
Key derivation function
-----------------------
With one exception, fscrypt never uses the master key(s) for
encryption directly. Instead, they are only used as input to a KDF
(Key Derivation Function) to derive the actual keys.
The KDF used for a particular master key differs depending on whether
the key is used for v1 encryption policies or for v2 encryption
policies. Users **must not** use the same key for both v1 and v2
encryption policies. (No real-world attack is currently known on this
specific case of key reuse, but its security cannot be guaranteed
since the cryptographic proofs and analysis would no longer apply.)
For v1 encryption policies, the KDF only supports deriving per-file
encryption keys. It works by encrypting the master key with
AES-128-ECB, using the file's 16-byte nonce as the AES key. The
resulting ciphertext is used as the derived key. If the ciphertext is
longer than needed, then it is truncated to the needed length.
For v2 encryption policies, the KDF is HKDF-SHA512. The master key is
passed as the "input keying material", no salt is used, and a distinct
"application-specific information string" is used for each distinct
key to be derived. For example, when a per-file encryption key is
derived, the application-specific information string is the file's
nonce prefixed with "fscrypt\\0" and a context byte. Different
context bytes are used for other types of derived keys.
HKDF-SHA512 is preferred to the original AES-128-ECB based KDF because
HKDF is more flexible, is nonreversible, and evenly distributes
entropy from the master key. HKDF is also standardized and widely
used by other software, whereas the AES-128-ECB based KDF is ad-hoc.
Per-file keys
-------------
@ -138,29 +243,9 @@ files doesn't map to the same ciphertext, or vice versa. In most
cases, fscrypt does this by deriving per-file keys. When a new
encrypted inode (regular file, directory, or symlink) is created,
fscrypt randomly generates a 16-byte nonce and stores it in the
inode's encryption xattr. Then, it uses a KDF (Key Derivation
Function) to derive the file's key from the master key and nonce.
The Adiantum encryption mode (see `Encryption modes and usage`_) is
special, since it accepts longer IVs and is suitable for both contents
and filenames encryption. For it, a "direct key" option is offered
where the file's nonce is included in the IVs and the master key is
used for encryption directly. This improves performance; however,
users must not use the same master key for any other encryption mode.
Below, the KDF and design considerations are described in more detail.
The current KDF works by encrypting the master key with AES-128-ECB,
using the file's nonce as the AES key. The output is used as the
derived key. If the output is longer than needed, then it is
truncated to the needed length.
Note: this KDF meets the primary security requirement, which is to
produce unique derived keys that preserve the entropy of the master
key, assuming that the master key is already a good pseudorandom key.
However, it is nonstandard and has some problems such as being
reversible, so it is generally considered to be a mistake! It may be
replaced with HKDF or another more standard KDF in the future.
inode's encryption xattr. Then, it uses a KDF (as described in `Key
derivation function`_) to derive the file's key from the master key
and nonce.
Key derivation was chosen over key wrapping because wrapped keys would
require larger xattrs which would be less likely to fit in-line in the
@ -176,6 +261,37 @@ rejected as it would have prevented ext4 filesystems from being
resized, and by itself still wouldn't have been sufficient to prevent
the same key from being directly reused for both XTS and CTS-CBC.
DIRECT_KEY and per-mode keys
----------------------------
The Adiantum encryption mode (see `Encryption modes and usage`_) is
suitable for both contents and filenames encryption, and it accepts
long IVs --- long enough to hold both an 8-byte logical block number
and a 16-byte per-file nonce. Also, the overhead of each Adiantum key
is greater than that of an AES-256-XTS key.
Therefore, to improve performance and save memory, for Adiantum a
"direct key" configuration is supported. When the user has enabled
this by setting FSCRYPT_POLICY_FLAG_DIRECT_KEY in the fscrypt policy,
per-file keys are not used. Instead, whenever any data (contents or
filenames) is encrypted, the file's 16-byte nonce is included in the
IV. Moreover:
- For v1 encryption policies, the encryption is done directly with the
master key. Because of this, users **must not** use the same master
key for any other purpose, even for other v1 policies.
- For v2 encryption policies, the encryption is done with a per-mode
key derived using the KDF. Users may use the same master key for
other v2 encryption policies.
Key identifiers
---------------
For master keys used for v2 encryption policies, a unique 16-byte "key
identifier" is also derived using the KDF. This value is stored in
the clear, since it is needed to reliably identify the key itself.
Encryption modes and usage
==========================
@ -225,9 +341,10 @@ a little endian number, except that:
is encrypted with AES-256 where the AES-256 key is the SHA-256 hash
of the file's data encryption key.
- In the "direct key" configuration (FS_POLICY_FLAG_DIRECT_KEY set in
the fscrypt_policy), the file's nonce is also appended to the IV.
Currently this is only allowed with the Adiantum encryption mode.
- In the "direct key" configuration (FSCRYPT_POLICY_FLAG_DIRECT_KEY
set in the fscrypt_policy), the file's nonce is also appended to the
IV. Currently this is only allowed with the Adiantum encryption
mode.
Filenames encryption
--------------------
@ -269,49 +386,77 @@ User API
Setting an encryption policy
----------------------------
FS_IOC_SET_ENCRYPTION_POLICY
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
The FS_IOC_SET_ENCRYPTION_POLICY ioctl sets an encryption policy on an
empty directory or verifies that a directory or regular file already
has the specified encryption policy. It takes in a pointer to a
:c:type:`struct fscrypt_policy`, defined as follows::
:c:type:`struct fscrypt_policy_v1` or a :c:type:`struct
fscrypt_policy_v2`, defined as follows::
#define FS_KEY_DESCRIPTOR_SIZE 8
struct fscrypt_policy {
#define FSCRYPT_POLICY_V1 0
#define FSCRYPT_KEY_DESCRIPTOR_SIZE 8
struct fscrypt_policy_v1 {
__u8 version;
__u8 contents_encryption_mode;
__u8 filenames_encryption_mode;
__u8 flags;
__u8 master_key_descriptor[FS_KEY_DESCRIPTOR_SIZE];
__u8 master_key_descriptor[FSCRYPT_KEY_DESCRIPTOR_SIZE];
};
#define fscrypt_policy fscrypt_policy_v1
#define FSCRYPT_POLICY_V2 2
#define FSCRYPT_KEY_IDENTIFIER_SIZE 16
struct fscrypt_policy_v2 {
__u8 version;
__u8 contents_encryption_mode;
__u8 filenames_encryption_mode;
__u8 flags;
__u8 __reserved[4];
__u8 master_key_identifier[FSCRYPT_KEY_IDENTIFIER_SIZE];
};
This structure must be initialized as follows:
- ``version`` must be 0.
- ``version`` must be FSCRYPT_POLICY_V1 (0) if the struct is
:c:type:`fscrypt_policy_v1` or FSCRYPT_POLICY_V2 (2) if the struct
is :c:type:`fscrypt_policy_v2`. (Note: we refer to the original
policy version as "v1", though its version code is really 0.) For
new encrypted directories, use v2 policies.
- ``contents_encryption_mode`` and ``filenames_encryption_mode`` must
be set to constants from ``<linux/fs.h>`` which identify the
encryption modes to use. If unsure, use
FS_ENCRYPTION_MODE_AES_256_XTS (1) for ``contents_encryption_mode``
and FS_ENCRYPTION_MODE_AES_256_CTS (4) for
``filenames_encryption_mode``.
be set to constants from ``<linux/fscrypt.h>`` which identify the
encryption modes to use. If unsure, use FSCRYPT_MODE_AES_256_XTS
(1) for ``contents_encryption_mode`` and FSCRYPT_MODE_AES_256_CTS
(4) for ``filenames_encryption_mode``.
- ``flags`` must contain a value from ``<linux/fs.h>`` which
- ``flags`` must contain a value from ``<linux/fscrypt.h>`` which
identifies the amount of NUL-padding to use when encrypting
filenames. If unsure, use FS_POLICY_FLAGS_PAD_32 (0x3).
In addition, if the chosen encryption modes are both
FS_ENCRYPTION_MODE_ADIANTUM, this can contain
FS_POLICY_FLAG_DIRECT_KEY to specify that the master key should be
used directly, without key derivation.
filenames. If unsure, use FSCRYPT_POLICY_FLAGS_PAD_32 (0x3).
Additionally, if the encryption modes are both
FSCRYPT_MODE_ADIANTUM, this can contain
FSCRYPT_POLICY_FLAG_DIRECT_KEY; see `DIRECT_KEY and per-mode keys`_.
- ``master_key_descriptor`` specifies how to find the master key in
the keyring; see `Adding keys`_. It is up to userspace to choose a
unique ``master_key_descriptor`` for each master key. The e4crypt
and fscrypt tools use the first 8 bytes of
- For v2 encryption policies, ``__reserved`` must be zeroed.
- For v1 encryption policies, ``master_key_descriptor`` specifies how
to find the master key in a keyring; see `Adding keys`_. It is up
to userspace to choose a unique ``master_key_descriptor`` for each
master key. The e4crypt and fscrypt tools use the first 8 bytes of
``SHA-512(SHA-512(master_key))``, but this particular scheme is not
required. Also, the master key need not be in the keyring yet when
FS_IOC_SET_ENCRYPTION_POLICY is executed. However, it must be added
before any files can be created in the encrypted directory.
For v2 encryption policies, ``master_key_descriptor`` has been
replaced with ``master_key_identifier``, which is longer and cannot
be arbitrarily chosen. Instead, the key must first be added using
`FS_IOC_ADD_ENCRYPTION_KEY`_. Then, the ``key_spec.u.identifier``
the kernel returned in the :c:type:`struct fscrypt_add_key_arg` must
be used as the ``master_key_identifier`` in the :c:type:`struct
fscrypt_policy_v2`.
If the file is not yet encrypted, then FS_IOC_SET_ENCRYPTION_POLICY
verifies that the file is an empty directory. If so, the specified
encryption policy is assigned to the directory, turning it into an
@ -327,6 +472,15 @@ policy exactly matches the actual one. If they match, then the ioctl
returns 0. Otherwise, it fails with EEXIST. This works on both
regular files and directories, including nonempty directories.
When a v2 encryption policy is assigned to a directory, it is also
required that either the specified key has been added by the current
user or that the caller has CAP_FOWNER in the initial user namespace.
(This is needed to prevent a user from encrypting their data with
another user's key.) The key must remain added while
FS_IOC_SET_ENCRYPTION_POLICY is executing. However, if the new
encrypted directory does not need to be accessed immediately, then the
key can be removed right away afterwards.
Note that the ext4 filesystem does not allow the root directory to be
encrypted, even if it is empty. Users who want to encrypt an entire
filesystem with one key should consider using dm-crypt instead.
@ -339,7 +493,11 @@ FS_IOC_SET_ENCRYPTION_POLICY can fail with the following errors:
- ``EEXIST``: the file is already encrypted with an encryption policy
different from the one specified
- ``EINVAL``: an invalid encryption policy was specified (invalid
version, mode(s), or flags)
version, mode(s), or flags; or reserved bits were set)
- ``ENOKEY``: a v2 encryption policy was specified, but the key with
the specified ``master_key_identifier`` has not been added, nor does
the process have the CAP_FOWNER capability in the initial user
namespace
- ``ENOTDIR``: the file is unencrypted and is a regular file, not a
directory
- ``ENOTEMPTY``: the file is unencrypted and is a nonempty directory
@ -358,25 +516,79 @@ FS_IOC_SET_ENCRYPTION_POLICY can fail with the following errors:
Getting an encryption policy
----------------------------
The FS_IOC_GET_ENCRYPTION_POLICY ioctl retrieves the :c:type:`struct
fscrypt_policy`, if any, for a directory or regular file. See above
for the struct definition. No additional permissions are required
beyond the ability to open the file.
Two ioctls are available to get a file's encryption policy:
FS_IOC_GET_ENCRYPTION_POLICY can fail with the following errors:
- `FS_IOC_GET_ENCRYPTION_POLICY_EX`_
- `FS_IOC_GET_ENCRYPTION_POLICY`_
The extended (_EX) version of the ioctl is more general and is
recommended to use when possible. However, on older kernels only the
original ioctl is available. Applications should try the extended
version, and if it fails with ENOTTY fall back to the original
version.
FS_IOC_GET_ENCRYPTION_POLICY_EX
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
The FS_IOC_GET_ENCRYPTION_POLICY_EX ioctl retrieves the encryption
policy, if any, for a directory or regular file. No additional
permissions are required beyond the ability to open the file. It
takes in a pointer to a :c:type:`struct fscrypt_get_policy_ex_arg`,
defined as follows::
struct fscrypt_get_policy_ex_arg {
__u64 policy_size; /* input/output */
union {
__u8 version;
struct fscrypt_policy_v1 v1;
struct fscrypt_policy_v2 v2;
} policy; /* output */
};
The caller must initialize ``policy_size`` to the size available for
the policy struct, i.e. ``sizeof(arg.policy)``.
On success, the policy struct is returned in ``policy``, and its
actual size is returned in ``policy_size``. ``policy.version`` should
be checked to determine the version of policy returned. Note that the
version code for the "v1" policy is actually 0 (FSCRYPT_POLICY_V1).
FS_IOC_GET_ENCRYPTION_POLICY_EX can fail with the following errors:
- ``EINVAL``: the file is encrypted, but it uses an unrecognized
encryption context format
encryption policy version
- ``ENODATA``: the file is not encrypted
- ``ENOTTY``: this type of filesystem does not implement encryption
- ``ENOTTY``: this type of filesystem does not implement encryption,
or this kernel is too old to support FS_IOC_GET_ENCRYPTION_POLICY_EX
(try FS_IOC_GET_ENCRYPTION_POLICY instead)
- ``EOPNOTSUPP``: the kernel was not configured with encryption
support for this filesystem
support for this filesystem, or the filesystem superblock has not
had encryption enabled on it
- ``EOVERFLOW``: the file is encrypted and uses a recognized
encryption policy version, but the policy struct does not fit into
the provided buffer
Note: if you only need to know whether a file is encrypted or not, on
most filesystems it is also possible to use the FS_IOC_GETFLAGS ioctl
and check for FS_ENCRYPT_FL, or to use the statx() system call and
check for STATX_ATTR_ENCRYPTED in stx_attributes.
FS_IOC_GET_ENCRYPTION_POLICY
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
The FS_IOC_GET_ENCRYPTION_POLICY ioctl can also retrieve the
encryption policy, if any, for a directory or regular file. However,
unlike `FS_IOC_GET_ENCRYPTION_POLICY_EX`_,
FS_IOC_GET_ENCRYPTION_POLICY only supports the original policy
version. It takes in a pointer directly to a :c:type:`struct
fscrypt_policy_v1` rather than a :c:type:`struct
fscrypt_get_policy_ex_arg`.
The error codes for FS_IOC_GET_ENCRYPTION_POLICY are the same as those
for FS_IOC_GET_ENCRYPTION_POLICY_EX, except that
FS_IOC_GET_ENCRYPTION_POLICY also returns ``EINVAL`` if the file is
encrypted using a newer encryption policy version.
Getting the per-filesystem salt
-------------------------------
@ -392,8 +604,115 @@ generate and manage any needed salt(s) in userspace.
Adding keys
-----------
To provide a master key, userspace must add it to an appropriate
keyring using the add_key() system call (see:
FS_IOC_ADD_ENCRYPTION_KEY
~~~~~~~~~~~~~~~~~~~~~~~~~
The FS_IOC_ADD_ENCRYPTION_KEY ioctl adds a master encryption key to
the filesystem, making all files on the filesystem which were
encrypted using that key appear "unlocked", i.e. in plaintext form.
It can be executed on any file or directory on the target filesystem,
but using the filesystem's root directory is recommended. It takes in
a pointer to a :c:type:`struct fscrypt_add_key_arg`, defined as
follows::
struct fscrypt_add_key_arg {
struct fscrypt_key_specifier key_spec;
__u32 raw_size;
__u32 __reserved[9];
__u8 raw[];
};
#define FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR 1
#define FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER 2
struct fscrypt_key_specifier {
__u32 type; /* one of FSCRYPT_KEY_SPEC_TYPE_* */
__u32 __reserved;
union {
__u8 __reserved[32]; /* reserve some extra space */
__u8 descriptor[FSCRYPT_KEY_DESCRIPTOR_SIZE];
__u8 identifier[FSCRYPT_KEY_IDENTIFIER_SIZE];
} u;
};
:c:type:`struct fscrypt_add_key_arg` must be zeroed, then initialized
as follows:
- If the key is being added for use by v1 encryption policies, then
``key_spec.type`` must contain FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR, and
``key_spec.u.descriptor`` must contain the descriptor of the key
being added, corresponding to the value in the
``master_key_descriptor`` field of :c:type:`struct
fscrypt_policy_v1`. To add this type of key, the calling process
must have the CAP_SYS_ADMIN capability in the initial user
namespace.
Alternatively, if the key is being added for use by v2 encryption
policies, then ``key_spec.type`` must contain
FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER, and ``key_spec.u.identifier`` is
an *output* field which the kernel fills in with a cryptographic
hash of the key. To add this type of key, the calling process does
not need any privileges. However, the number of keys that can be
added is limited by the user's quota for the keyrings service (see
``Documentation/security/keys/core.rst``).
- ``raw_size`` must be the size of the ``raw`` key provided, in bytes.
- ``raw`` is a variable-length field which must contain the actual
key, ``raw_size`` bytes long.
For v2 policy keys, the kernel keeps track of which user (identified
by effective user ID) added the key, and only allows the key to be
removed by that user --- or by "root", if they use
`FS_IOC_REMOVE_ENCRYPTION_KEY_ALL_USERS`_.
However, if another user has added the key, it may be desirable to
prevent that other user from unexpectedly removing it. Therefore,
FS_IOC_ADD_ENCRYPTION_KEY may also be used to add a v2 policy key
*again*, even if it's already added by other user(s). In this case,
FS_IOC_ADD_ENCRYPTION_KEY will just install a claim to the key for the
current user, rather than actually add the key again (but the raw key
must still be provided, as a proof of knowledge).
FS_IOC_ADD_ENCRYPTION_KEY returns 0 if either the key or a claim to
the key was either added or already exists.
FS_IOC_ADD_ENCRYPTION_KEY can fail with the following errors:
- ``EACCES``: FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR was specified, but the
caller does not have the CAP_SYS_ADMIN capability in the initial
user namespace
- ``EDQUOT``: the key quota for this user would be exceeded by adding
the key
- ``EINVAL``: invalid key size or key specifier type, or reserved bits
were set
- ``ENOTTY``: this type of filesystem does not implement encryption
- ``EOPNOTSUPP``: the kernel was not configured with encryption
support for this filesystem, or the filesystem superblock has not
had encryption enabled on it
Legacy method
~~~~~~~~~~~~~
For v1 encryption policies, a master encryption key can also be
provided by adding it to a process-subscribed keyring, e.g. to a
session keyring, or to a user keyring if the user keyring is linked
into the session keyring.
This method is deprecated (and not supported for v2 encryption
policies) for several reasons. First, it cannot be used in
combination with FS_IOC_REMOVE_ENCRYPTION_KEY (see `Removing keys`_),
so for removing a key a workaround such as keyctl_unlink() in
combination with ``sync; echo 2 > /proc/sys/vm/drop_caches`` would
have to be used. Second, it doesn't match the fact that the
locked/unlocked status of encrypted files (i.e. whether they appear to
be in plaintext form or in ciphertext form) is global. This mismatch
has caused much confusion as well as real problems when processes
running under different UIDs, such as a ``sudo`` command, need to
access encrypted files.
Nevertheless, to add a key to one of the process-subscribed keyrings,
the add_key() system call can be used (see:
``Documentation/security/keys/core.rst``). The key type must be
"logon"; keys of this type are kept in kernel memory and cannot be
read back by userspace. The key description must be "fscrypt:"
@ -401,12 +720,12 @@ followed by the 16-character lower case hex representation of the
``master_key_descriptor`` that was set in the encryption policy. The
key payload must conform to the following structure::
#define FS_MAX_KEY_SIZE 64
#define FSCRYPT_MAX_KEY_SIZE 64
struct fscrypt_key {
u32 mode;
u8 raw[FS_MAX_KEY_SIZE];
u32 size;
__u32 mode;
__u8 raw[FSCRYPT_MAX_KEY_SIZE];
__u32 size;
};
``mode`` is ignored; just set it to 0. The actual key is provided in
@ -418,26 +737,194 @@ with a filesystem-specific prefix such as "ext4:". However, the
filesystem-specific prefixes are deprecated and should not be used in
new programs.
There are several different types of keyrings in which encryption keys
may be placed, such as a session keyring, a user session keyring, or a
user keyring. Each key must be placed in a keyring that is "attached"
to all processes that might need to access files encrypted with it, in
the sense that request_key() will find the key. Generally, if only
processes belonging to a specific user need to access a given
encrypted directory and no session keyring has been installed, then
that directory's key should be placed in that user's user session
keyring or user keyring. Otherwise, a session keyring should be
installed if needed, and the key should be linked into that session
keyring, or in a keyring linked into that session keyring.
Removing keys
-------------
Note: introducing the complex visibility semantics of keyrings here
was arguably a mistake --- especially given that by design, after any
process successfully opens an encrypted file (thereby setting up the
per-file key), possessing the keyring key is not actually required for
any process to read/write the file until its in-memory inode is
evicted. In the future there probably should be a way to provide keys
directly to the filesystem instead, which would make the intended
semantics clearer.
Two ioctls are available for removing a key that was added by
`FS_IOC_ADD_ENCRYPTION_KEY`_:
- `FS_IOC_REMOVE_ENCRYPTION_KEY`_
- `FS_IOC_REMOVE_ENCRYPTION_KEY_ALL_USERS`_
These two ioctls differ only in cases where v2 policy keys are added
or removed by non-root users.
These ioctls don't work on keys that were added via the legacy
process-subscribed keyrings mechanism.
Before using these ioctls, read the `Kernel memory compromise`_
section for a discussion of the security goals and limitations of
these ioctls.
FS_IOC_REMOVE_ENCRYPTION_KEY
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
The FS_IOC_REMOVE_ENCRYPTION_KEY ioctl removes a claim to a master
encryption key from the filesystem, and possibly removes the key
itself. It can be executed on any file or directory on the target
filesystem, but using the filesystem's root directory is recommended.
It takes in a pointer to a :c:type:`struct fscrypt_remove_key_arg`,
defined as follows::
struct fscrypt_remove_key_arg {
struct fscrypt_key_specifier key_spec;
#define FSCRYPT_KEY_REMOVAL_STATUS_FLAG_FILES_BUSY 0x00000001
#define FSCRYPT_KEY_REMOVAL_STATUS_FLAG_OTHER_USERS 0x00000002
__u32 removal_status_flags; /* output */
__u32 __reserved[5];
};
This structure must be zeroed, then initialized as follows:
- The key to remove is specified by ``key_spec``:
- To remove a key used by v1 encryption policies, set
``key_spec.type`` to FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR and fill
in ``key_spec.u.descriptor``. To remove this type of key, the
calling process must have the CAP_SYS_ADMIN capability in the
initial user namespace.
- To remove a key used by v2 encryption policies, set
``key_spec.type`` to FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER and fill
in ``key_spec.u.identifier``.
For v2 policy keys, this ioctl is usable by non-root users. However,
to make this possible, it actually just removes the current user's
claim to the key, undoing a single call to FS_IOC_ADD_ENCRYPTION_KEY.
Only after all claims are removed is the key really removed.
For example, if FS_IOC_ADD_ENCRYPTION_KEY was called with uid 1000,
then the key will be "claimed" by uid 1000, and
FS_IOC_REMOVE_ENCRYPTION_KEY will only succeed as uid 1000. Or, if
both uids 1000 and 2000 added the key, then for each uid
FS_IOC_REMOVE_ENCRYPTION_KEY will only remove their own claim. Only
once *both* are removed is the key really removed. (Think of it like
unlinking a file that may have hard links.)
If FS_IOC_REMOVE_ENCRYPTION_KEY really removes the key, it will also
try to "lock" all files that had been unlocked with the key. It won't
lock files that are still in-use, so this ioctl is expected to be used
in cooperation with userspace ensuring that none of the files are
still open. However, if necessary, this ioctl can be executed again
later to retry locking any remaining files.
FS_IOC_REMOVE_ENCRYPTION_KEY returns 0 if either the key was removed
(but may still have files remaining to be locked), the user's claim to
the key was removed, or the key was already removed but had files
remaining to be the locked so the ioctl retried locking them. In any
of these cases, ``removal_status_flags`` is filled in with the
following informational status flags:
- ``FSCRYPT_KEY_REMOVAL_STATUS_FLAG_FILES_BUSY``: set if some file(s)
are still in-use. Not guaranteed to be set in the case where only
the user's claim to the key was removed.
- ``FSCRYPT_KEY_REMOVAL_STATUS_FLAG_OTHER_USERS``: set if only the
user's claim to the key was removed, not the key itself
FS_IOC_REMOVE_ENCRYPTION_KEY can fail with the following errors:
- ``EACCES``: The FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR key specifier type
was specified, but the caller does not have the CAP_SYS_ADMIN
capability in the initial user namespace
- ``EINVAL``: invalid key specifier type, or reserved bits were set
- ``ENOKEY``: the key object was not found at all, i.e. it was never
added in the first place or was already fully removed including all
files locked; or, the user does not have a claim to the key (but
someone else does).
- ``ENOTTY``: this type of filesystem does not implement encryption
- ``EOPNOTSUPP``: the kernel was not configured with encryption
support for this filesystem, or the filesystem superblock has not
had encryption enabled on it
FS_IOC_REMOVE_ENCRYPTION_KEY_ALL_USERS
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
FS_IOC_REMOVE_ENCRYPTION_KEY_ALL_USERS is exactly the same as
`FS_IOC_REMOVE_ENCRYPTION_KEY`_, except that for v2 policy keys, the
ALL_USERS version of the ioctl will remove all users' claims to the
key, not just the current user's. I.e., the key itself will always be
removed, no matter how many users have added it. This difference is
only meaningful if non-root users are adding and removing keys.
Because of this, FS_IOC_REMOVE_ENCRYPTION_KEY_ALL_USERS also requires
"root", namely the CAP_SYS_ADMIN capability in the initial user
namespace. Otherwise it will fail with EACCES.
Getting key status
------------------
FS_IOC_GET_ENCRYPTION_KEY_STATUS
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
The FS_IOC_GET_ENCRYPTION_KEY_STATUS ioctl retrieves the status of a
master encryption key. It can be executed on any file or directory on
the target filesystem, but using the filesystem's root directory is
recommended. It takes in a pointer to a :c:type:`struct
fscrypt_get_key_status_arg`, defined as follows::
struct fscrypt_get_key_status_arg {
/* input */
struct fscrypt_key_specifier key_spec;
__u32 __reserved[6];
/* output */
#define FSCRYPT_KEY_STATUS_ABSENT 1
#define FSCRYPT_KEY_STATUS_PRESENT 2
#define FSCRYPT_KEY_STATUS_INCOMPLETELY_REMOVED 3
__u32 status;
#define FSCRYPT_KEY_STATUS_FLAG_ADDED_BY_SELF 0x00000001
__u32 status_flags;
__u32 user_count;
__u32 __out_reserved[13];
};
The caller must zero all input fields, then fill in ``key_spec``:
- To get the status of a key for v1 encryption policies, set
``key_spec.type`` to FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR and fill
in ``key_spec.u.descriptor``.
- To get the status of a key for v2 encryption policies, set
``key_spec.type`` to FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER and fill
in ``key_spec.u.identifier``.
On success, 0 is returned and the kernel fills in the output fields:
- ``status`` indicates whether the key is absent, present, or
incompletely removed. Incompletely removed means that the master
secret has been removed, but some files are still in use; i.e.,
`FS_IOC_REMOVE_ENCRYPTION_KEY`_ returned 0 but set the informational
status flag FSCRYPT_KEY_REMOVAL_STATUS_FLAG_FILES_BUSY.
- ``status_flags`` can contain the following flags:
- ``FSCRYPT_KEY_STATUS_FLAG_ADDED_BY_SELF`` indicates that the key
has added by the current user. This is only set for keys
identified by ``identifier`` rather than by ``descriptor``.
- ``user_count`` specifies the number of users who have added the key.
This is only set for keys identified by ``identifier`` rather than
by ``descriptor``.
FS_IOC_GET_ENCRYPTION_KEY_STATUS can fail with the following errors:
- ``EINVAL``: invalid key specifier type, or reserved bits were set
- ``ENOTTY``: this type of filesystem does not implement encryption
- ``EOPNOTSUPP``: the kernel was not configured with encryption
support for this filesystem, or the filesystem superblock has not
had encryption enabled on it
Among other use cases, FS_IOC_GET_ENCRYPTION_KEY_STATUS can be useful
for determining whether the key for a given encrypted directory needs
to be added before prompting the user for the passphrase needed to
derive the key.
FS_IOC_GET_ENCRYPTION_KEY_STATUS can only get the status of keys in
the filesystem-level keyring, i.e. the keyring managed by
`FS_IOC_ADD_ENCRYPTION_KEY`_ and `FS_IOC_REMOVE_ENCRYPTION_KEY`_. It
cannot get the status of a key that has only been added for use by v1
encryption policies using the legacy mechanism involving
process-subscribed keyrings.
Access semantics
================
@ -500,7 +987,7 @@ Without the key
Some filesystem operations may be performed on encrypted regular
files, directories, and symlinks even before their encryption key has
been provided:
been added, or after their encryption key has been removed:
- File metadata may be read, e.g. using stat().
@ -565,33 +1052,44 @@ Encryption context
------------------
An encryption policy is represented on-disk by a :c:type:`struct
fscrypt_context`. It is up to individual filesystems to decide where
to store it, but normally it would be stored in a hidden extended
attribute. It should *not* be exposed by the xattr-related system
calls such as getxattr() and setxattr() because of the special
semantics of the encryption xattr. (In particular, there would be
much confusion if an encryption policy were to be added to or removed
from anything other than an empty directory.) The struct is defined
as follows::
fscrypt_context_v1` or a :c:type:`struct fscrypt_context_v2`. It is
up to individual filesystems to decide where to store it, but normally
it would be stored in a hidden extended attribute. It should *not* be
exposed by the xattr-related system calls such as getxattr() and
setxattr() because of the special semantics of the encryption xattr.
(In particular, there would be much confusion if an encryption policy
were to be added to or removed from anything other than an empty
directory.) These structs are defined as follows::
#define FS_KEY_DESCRIPTOR_SIZE 8
#define FS_KEY_DERIVATION_NONCE_SIZE 16
struct fscrypt_context {
u8 format;
#define FSCRYPT_KEY_DESCRIPTOR_SIZE 8
struct fscrypt_context_v1 {
u8 version;
u8 contents_encryption_mode;
u8 filenames_encryption_mode;
u8 flags;
u8 master_key_descriptor[FS_KEY_DESCRIPTOR_SIZE];
u8 master_key_descriptor[FSCRYPT_KEY_DESCRIPTOR_SIZE];
u8 nonce[FS_KEY_DERIVATION_NONCE_SIZE];
};
Note that :c:type:`struct fscrypt_context` contains the same
information as :c:type:`struct fscrypt_policy` (see `Setting an
encryption policy`_), except that :c:type:`struct fscrypt_context`
also contains a nonce. The nonce is randomly generated by the kernel
and is used to derive the inode's encryption key as described in
`Per-file keys`_.
#define FSCRYPT_KEY_IDENTIFIER_SIZE 16
struct fscrypt_context_v2 {
u8 version;
u8 contents_encryption_mode;
u8 filenames_encryption_mode;
u8 flags;
u8 __reserved[4];
u8 master_key_identifier[FSCRYPT_KEY_IDENTIFIER_SIZE];
u8 nonce[FS_KEY_DERIVATION_NONCE_SIZE];
};
The context structs contain the same information as the corresponding
policy structs (see `Setting an encryption policy`_), except that the
context structs also contain a nonce. The nonce is randomly generated
by the kernel and is used as KDF input or as a tweak to cause
different files to be encrypted differently; see `Per-file keys`_ and
`DIRECT_KEY and per-mode keys`_.
Data path changes
-----------------

726
Documentation/filesystems/fsverity.rst Normal file
View file

@ -0,0 +1,726 @@
.. SPDX-License-Identifier: GPL-2.0
.. _fsverity:
=======================================================
fs-verity: read-only file-based authenticity protection
=======================================================
Introduction
============
fs-verity (``fs/verity/``) is a support layer that filesystems can
hook into to support transparent integrity and authenticity protection
of read-only files. Currently, it is supported by the ext4 and f2fs
filesystems. Like fscrypt, not too much filesystem-specific code is
needed to support fs-verity.
fs-verity is similar to `dm-verity
<https://www.kernel.org/doc/Documentation/device-mapper/verity.txt>`_
but works on files rather than block devices. On regular files on
filesystems supporting fs-verity, userspace can execute an ioctl that
causes the filesystem to build a Merkle tree for the file and persist
it to a filesystem-specific location associated with the file.
After this, the file is made readonly, and all reads from the file are
automatically verified against the file's Merkle tree. Reads of any
corrupted data, including mmap reads, will fail.
Userspace can use another ioctl to retrieve the root hash (actually
the "file measurement", which is a hash that includes the root hash)
that fs-verity is enforcing for the file. This ioctl executes in
constant time, regardless of the file size.
fs-verity is essentially a way to hash a file in constant time,
subject to the caveat that reads which would violate the hash will
fail at runtime.
Use cases
=========
By itself, the base fs-verity feature only provides integrity
protection, i.e. detection of accidental (non-malicious) corruption.
However, because fs-verity makes retrieving the file hash extremely
efficient, it's primarily meant to be used as a tool to support
authentication (detection of malicious modifications) or auditing
(logging file hashes before use).
Trusted userspace code (e.g. operating system code running on a
read-only partition that is itself authenticated by dm-verity) can
authenticate the contents of an fs-verity file by using the
`FS_IOC_MEASURE_VERITY`_ ioctl to retrieve its hash, then verifying a
digital signature of it.
A standard file hash could be used instead of fs-verity. However,
this is inefficient if the file is large and only a small portion may
be accessed. This is often the case for Android application package
(APK) files, for example. These typically contain many translations,
classes, and other resources that are infrequently or even never
accessed on a particular device. It would be slow and wasteful to
read and hash the entire file before starting the application.
Unlike an ahead-of-time hash, fs-verity also re-verifies data each
time it's paged in. This ensures that malicious disk firmware can't
undetectably change the contents of the file at runtime.
fs-verity does not replace or obsolete dm-verity. dm-verity should
still be used on read-only filesystems. fs-verity is for files that
must live on a read-write filesystem because they are independently
updated and potentially user-installed, so dm-verity cannot be used.
The base fs-verity feature is a hashing mechanism only; actually
authenticating the files is up to userspace. However, to meet some
users' needs, fs-verity optionally supports a simple signature
verification mechanism where users can configure the kernel to require
that all fs-verity files be signed by a key loaded into a keyring; see
`Built-in signature verification`_. Support for fs-verity file hashes
in IMA (Integrity Measurement Architecture) policies is also planned.
User API
========
FS_IOC_ENABLE_VERITY
--------------------
The FS_IOC_ENABLE_VERITY ioctl enables fs-verity on a file. It takes
in a pointer to a :c:type:`struct fsverity_enable_arg`, defined as
follows::
struct fsverity_enable_arg {
__u32 version;
__u32 hash_algorithm;
__u32 block_size;
__u32 salt_size;
__u64 salt_ptr;
__u32 sig_size;
__u32 __reserved1;
__u64 sig_ptr;
__u64 __reserved2[11];
};
This structure contains the parameters of the Merkle tree to build for
the file, and optionally contains a signature. It must be initialized
as follows:
- ``version`` must be 1.
- ``hash_algorithm`` must be the identifier for the hash algorithm to
use for the Merkle tree, such as FS_VERITY_HASH_ALG_SHA256. See
``include/uapi/linux/fsverity.h`` for the list of possible values.
- ``block_size`` must be the Merkle tree block size. Currently, this
must be equal to the system page size, which is usually 4096 bytes.
Other sizes may be supported in the future. This value is not
necessarily the same as the filesystem block size.
- ``salt_size`` is the size of the salt in bytes, or 0 if no salt is
provided. The salt is a value that is prepended to every hashed
block; it can be used to personalize the hashing for a particular
file or device. Currently the maximum salt size is 32 bytes.
- ``salt_ptr`` is the pointer to the salt, or NULL if no salt is
provided.
- ``sig_size`` is the size of the signature in bytes, or 0 if no
signature is provided. Currently the signature is (somewhat
arbitrarily) limited to 16128 bytes. See `Built-in signature
verification`_ for more information.
- ``sig_ptr`` is the pointer to the signature, or NULL if no
signature is provided.
- All reserved fields must be zeroed.
FS_IOC_ENABLE_VERITY causes the filesystem to build a Merkle tree for
the file and persist it to a filesystem-specific location associated
with the file, then mark the file as a verity file. This ioctl may
take a long time to execute on large files, and it is interruptible by
fatal signals.
FS_IOC_ENABLE_VERITY checks for write access to the inode. However,
it must be executed on an O_RDONLY file descriptor and no processes
can have the file open for writing. Attempts to open the file for
writing while this ioctl is executing will fail with ETXTBSY. (This
is necessary to guarantee that no writable file descriptors will exist
after verity is enabled, and to guarantee that the file's contents are
stable while the Merkle tree is being built over it.)
On success, FS_IOC_ENABLE_VERITY returns 0, and the file becomes a
verity file. On failure (including the case of interruption by a
fatal signal), no changes are made to the file.
FS_IOC_ENABLE_VERITY can fail with the following errors:
- ``EACCES``: the process does not have write access to the file
- ``EBADMSG``: the signature is malformed
- ``EBUSY``: this ioctl is already running on the file
- ``EEXIST``: the file already has verity enabled
- ``EFAULT``: the caller provided inaccessible memory
- ``EINTR``: the operation was interrupted by a fatal signal
- ``EINVAL``: unsupported version, hash algorithm, or block size; or
reserved bits are set; or the file descriptor refers to neither a
regular file nor a directory.
- ``EISDIR``: the file descriptor refers to a directory
- ``EKEYREJECTED``: the signature doesn't match the file
- ``EMSGSIZE``: the salt or signature is too long
- ``ENOKEY``: the fs-verity keyring doesn't contain the certificate
needed to verify the signature
- ``ENOPKG``: fs-verity recognizes the hash algorithm, but it's not
available in the kernel's crypto API as currently configured (e.g.
for SHA-512, missing CONFIG_CRYPTO_SHA512).
- ``ENOTTY``: this type of filesystem does not implement fs-verity
- ``EOPNOTSUPP``: the kernel was not configured with fs-verity
support; or the filesystem superblock has not had the 'verity'
feature enabled on it; or the filesystem does not support fs-verity
on this file. (See `Filesystem support`_.)
- ``EPERM``: the file is append-only; or, a signature is required and
one was not provided.
- ``EROFS``: the filesystem is read-only
- ``ETXTBSY``: someone has the file open for writing. This can be the
caller's file descriptor, another open file descriptor, or the file
reference held by a writable memory map.
FS_IOC_MEASURE_VERITY
---------------------
The FS_IOC_MEASURE_VERITY ioctl retrieves the measurement of a verity
file. The file measurement is a digest that cryptographically
identifies the file contents that are being enforced on reads.
This ioctl takes in a pointer to a variable-length structure::
struct fsverity_digest {
__u16 digest_algorithm;
__u16 digest_size; /* input/output */
__u8 digest[];
};
``digest_size`` is an input/output field. On input, it must be
initialized to the number of bytes allocated for the variable-length
``digest`` field.
On success, 0 is returned and the kernel fills in the structure as
follows:
- ``digest_algorithm`` will be the hash algorithm used for the file
measurement. It will match ``fsverity_enable_arg::hash_algorithm``.
- ``digest_size`` will be the size of the digest in bytes, e.g. 32
for SHA-256. (This can be redundant with ``digest_algorithm``.)
- ``digest`` will be the actual bytes of the digest.
FS_IOC_MEASURE_VERITY is guaranteed to execute in constant time,
regardless of the size of the file.
FS_IOC_MEASURE_VERITY can fail with the following errors:
- ``EFAULT``: the caller provided inaccessible memory
- ``ENODATA``: the file is not a verity file
- ``ENOTTY``: this type of filesystem does not implement fs-verity
- ``EOPNOTSUPP``: the kernel was not configured with fs-verity
support, or the filesystem superblock has not had the 'verity'
feature enabled on it. (See `Filesystem support`_.)
- ``EOVERFLOW``: the digest is longer than the specified
``digest_size`` bytes. Try providing a larger buffer.
FS_IOC_GETFLAGS
---------------
The existing ioctl FS_IOC_GETFLAGS (which isn't specific to fs-verity)
can also be used to check whether a file has fs-verity enabled or not.
To do so, check for FS_VERITY_FL (0x00100000) in the returned flags.
The verity flag is not settable via FS_IOC_SETFLAGS. You must use
FS_IOC_ENABLE_VERITY instead, since parameters must be provided.
Accessing verity files
======================
Applications can transparently access a verity file just like a
non-verity one, with the following exceptions:
- Verity files are readonly. They cannot be opened for writing or
truncate()d, even if the file mode bits allow it. Attempts to do
one of these things will fail with EPERM. However, changes to
metadata such as owner, mode, timestamps, and xattrs are still
allowed, since these are not measured by fs-verity. Verity files
can also still be renamed, deleted, and linked to.
- Direct I/O is not supported on verity files. Attempts to use direct
I/O on such files will fall back to buffered I/O.
- DAX (Direct Access) is not supported on verity files, because this
would circumvent the data verification.
- Reads of data that doesn't match the verity Merkle tree will fail
with EIO (for read()) or SIGBUS (for mmap() reads).
- If the sysctl "fs.verity.require_signatures" is set to 1 and the
file's verity measurement is not signed by a key in the fs-verity
keyring, then opening the file will fail. See `Built-in signature
verification`_.
Direct access to the Merkle tree is not supported. Therefore, if a
verity file is copied, or is backed up and restored, then it will lose
its "verity"-ness. fs-verity is primarily meant for files like
executables that are managed by a package manager.
File measurement computation
============================
This section describes how fs-verity hashes the file contents using a
Merkle tree to produce the "file measurement" which cryptographically
identifies the file contents. This algorithm is the same for all
filesystems that support fs-verity.
Userspace only needs to be aware of this algorithm if it needs to
compute the file measurement itself, e.g. in order to sign the file.
.. _fsverity_merkle_tree:
Merkle tree
-----------
The file contents is divided into blocks, where the block size is
configurable but is usually 4096 bytes. The end of the last block is
zero-padded if needed. Each block is then hashed, producing the first
level of hashes. Then, the hashes in this first level are grouped
into 'blocksize'-byte blocks (zero-padding the ends as needed) and
these blocks are hashed, producing the second level of hashes. This
proceeds up the tree until only a single block remains. The hash of
this block is the "Merkle tree root hash".
If the file fits in one block and is nonempty, then the "Merkle tree
root hash" is simply the hash of the single data block. If the file
is empty, then the "Merkle tree root hash" is all zeroes.
The "blocks" here are not necessarily the same as "filesystem blocks".
If a salt was specified, then it's zero-padded to the closest multiple
of the input size of the hash algorithm's compression function, e.g.
64 bytes for SHA-256 or 128 bytes for SHA-512. The padded salt is
prepended to every data or Merkle tree block that is hashed.
The purpose of the block padding is to cause every hash to be taken
over the same amount of data, which simplifies the implementation and
keeps open more possibilities for hardware acceleration. The purpose
of the salt padding is to make the salting "free" when the salted hash
state is precomputed, then imported for each hash.
Example: in the recommended configuration of SHA-256 and 4K blocks,
128 hash values fit in each block. Thus, each level of the Merkle
tree is approximately 128 times smaller than the previous, and for
large files the Merkle tree's size converges to approximately 1/127 of
the original file size. However, for small files, the padding is
significant, making the space overhead proportionally more.
.. _fsverity_descriptor:
fs-verity descriptor
--------------------
By itself, the Merkle tree root hash is ambiguous. For example, it
can't a distinguish a large file from a small second file whose data
is exactly the top-level hash block of the first file. Ambiguities
also arise from the convention of padding to the next block boundary.
To solve this problem, the verity file measurement is actually
computed as a hash of the following structure, which contains the
Merkle tree root hash as well as other fields such as the file size::
struct fsverity_descriptor {
__u8 version; /* must be 1 */
__u8 hash_algorithm; /* Merkle tree hash algorithm */
__u8 log_blocksize; /* log2 of size of data and tree blocks */
__u8 salt_size; /* size of salt in bytes; 0 if none */
__le32 sig_size; /* must be 0 */
__le64 data_size; /* size of file the Merkle tree is built over */
__u8 root_hash[64]; /* Merkle tree root hash */
__u8 salt[32]; /* salt prepended to each hashed block */
__u8 __reserved[144]; /* must be 0's */
};
Note that the ``sig_size`` field must be set to 0 for the purpose of
computing the file measurement, even if a signature was provided (or
will be provided) to `FS_IOC_ENABLE_VERITY`_.
Built-in signature verification
===============================
With CONFIG_FS_VERITY_BUILTIN_SIGNATURES=y, fs-verity supports putting
a portion of an authentication policy (see `Use cases`_) in the
kernel. Specifically, it adds support for:
1. At fs-verity module initialization time, a keyring ".fs-verity" is
created. The root user can add trusted X.509 certificates to this
keyring using the add_key() system call, then (when done)
optionally use keyctl_restrict_keyring() to prevent additional
certificates from being added.
2. `FS_IOC_ENABLE_VERITY`_ accepts a pointer to a PKCS#7 formatted
detached signature in DER format of the file measurement. On
success, this signature is persisted alongside the Merkle tree.
Then, any time the file is opened, the kernel will verify the
file's actual measurement against this signature, using the
certificates in the ".fs-verity" keyring.
3. A new sysctl "fs.verity.require_signatures" is made available.
When set to 1, the kernel requires that all verity files have a
correctly signed file measurement as described in (2).
File measurements must be signed in the following format, which is
similar to the structure used by `FS_IOC_MEASURE_VERITY`_::
struct fsverity_signed_digest {
char magic[8]; /* must be "FSVerity" */
__le16 digest_algorithm;
__le16 digest_size;
__u8 digest[];
};
fs-verity's built-in signature verification support is meant as a
relatively simple mechanism that can be used to provide some level of
authenticity protection for verity files, as an alternative to doing
the signature verification in userspace or using IMA-appraisal.
However, with this mechanism, userspace programs still need to check
that the verity bit is set, and there is no protection against verity
files being swapped around.
Filesystem support
==================
fs-verity is currently supported by the ext4 and f2fs filesystems.
The CONFIG_FS_VERITY kconfig option must be enabled to use fs-verity
on either filesystem.
``include/linux/fsverity.h`` declares the interface between the
``fs/verity/`` support layer and filesystems. Briefly, filesystems
must provide an ``fsverity_operations`` structure that provides
methods to read and write the verity metadata to a filesystem-specific
location, including the Merkle tree blocks and
``fsverity_descriptor``. Filesystems must also call functions in
``fs/verity/`` at certain times, such as when a file is opened or when
pages have been read into the pagecache. (See `Verifying data`_.)
ext4
----
ext4 supports fs-verity since Linux TODO and e2fsprogs v1.45.2.
To create verity files on an ext4 filesystem, the filesystem must have
been formatted with ``-O verity`` or had ``tune2fs -O verity`` run on
it. "verity" is an RO_COMPAT filesystem feature, so once set, old
kernels will only be able to mount the filesystem readonly, and old
versions of e2fsck will be unable to check the filesystem. Moreover,
currently ext4 only supports mounting a filesystem with the "verity"
feature when its block size is equal to PAGE_SIZE (often 4096 bytes).
ext4 sets the EXT4_VERITY_FL on-disk inode flag on verity files. It
can only be set by `FS_IOC_ENABLE_VERITY`_, and it cannot be cleared.
ext4 also supports encryption, which can be used simultaneously with
fs-verity. In this case, the plaintext data is verified rather than
the ciphertext. This is necessary in order to make the file
measurement meaningful, since every file is encrypted differently.
ext4 stores the verity metadata (Merkle tree and fsverity_descriptor)
past the end of the file, starting at the first 64K boundary beyond
i_size. This approach works because (a) verity files are readonly,
and (b) pages fully beyond i_size aren't visible to userspace but can
be read/written internally by ext4 with only some relatively small
changes to ext4. This approach avoids having to depend on the
EA_INODE feature and on rearchitecturing ext4's xattr support to
support paging multi-gigabyte xattrs into memory, and to support
encrypting xattrs. Note that the verity metadata *must* be encrypted
when the file is, since it contains hashes of the plaintext data.
Currently, ext4 verity only supports the case where the Merkle tree
block size, filesystem block size, and page size are all the same. It
also only supports extent-based files.
f2fs
----
f2fs supports fs-verity since Linux TODO and f2fs-tools v1.11.0.
To create verity files on an f2fs filesystem, the filesystem must have
been formatted with ``-O verity``.
f2fs sets the FADVISE_VERITY_BIT on-disk inode flag on verity files.
It can only be set by `FS_IOC_ENABLE_VERITY`_, and it cannot be
cleared.
Like ext4, f2fs stores the verity metadata (Merkle tree and
fsverity_descriptor) past the end of the file, starting at the first
64K boundary beyond i_size. See explanation for ext4 above.
Moreover, f2fs supports at most 4096 bytes of xattr entries per inode
which wouldn't be enough for even a single Merkle tree block.
Currently, f2fs verity only supports a Merkle tree block size of 4096.
Also, f2fs doesn't support enabling verity on files that currently
have atomic or volatile writes pending.
Implementation details
======================
Verifying data
--------------
fs-verity ensures that all reads of a verity file's data are verified,
regardless of which syscall is used to do the read (e.g. mmap(),
read(), pread()) and regardless of whether it's the first read or a
later read (unless the later read can return cached data that was
already verified). Below, we describe how filesystems implement this.
Pagecache
~~~~~~~~~
For filesystems using Linux's pagecache, the ``->readpage()`` and
``->readpages()`` methods must be modified to verify pages before they
are marked Uptodate. Merely hooking ``->read_iter()`` would be
insufficient, since ``->read_iter()`` is not used for memory maps.
Therefore, fs/verity/ provides a function fsverity_verify_page() which
verifies a page that has been read into the pagecache of a verity
inode, but is still locked and not Uptodate, so it's not yet readable
by userspace. As needed to do the verification,
fsverity_verify_page() will call back into the filesystem to read
Merkle tree pages via fsverity_operations::read_merkle_tree_page().
fsverity_verify_page() returns false if verification failed; in this
case, the filesystem must not set the page Uptodate. Following this,
as per the usual Linux pagecache behavior, attempts by userspace to
read() from the part of the file containing the page will fail with
EIO, and accesses to the page within a memory map will raise SIGBUS.
fsverity_verify_page() currently only supports the case where the
Merkle tree block size is equal to PAGE_SIZE (often 4096 bytes).
In principle, fsverity_verify_page() verifies the entire path in the
Merkle tree from the data page to the root hash. However, for
efficiency the filesystem may cache the hash pages. Therefore,
fsverity_verify_page() only ascends the tree reading hash pages until
an already-verified hash page is seen, as indicated by the PageChecked
bit being set. It then verifies the path to that page.
This optimization, which is also used by dm-verity, results in
excellent sequential read performance. This is because usually (e.g.
127 in 128 times for 4K blocks and SHA-256) the hash page from the
bottom level of the tree will already be cached and checked from
reading a previous data page. However, random reads perform worse.
Block device based filesystems
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Block device based filesystems (e.g. ext4 and f2fs) in Linux also use
the pagecache, so the above subsection applies too. However, they
also usually read many pages from a file at once, grouped into a
structure called a "bio". To make it easier for these types of
filesystems to support fs-verity, fs/verity/ also provides a function
fsverity_verify_bio() which verifies all pages in a bio.
ext4 and f2fs also support encryption. If a verity file is also
encrypted, the pages must be decrypted before being verified. To
support this, these filesystems allocate a "post-read context" for
each bio and store it in ``->bi_private``::
struct bio_post_read_ctx {
struct bio *bio;
struct work_struct work;
unsigned int cur_step;
unsigned int enabled_steps;
};
``enabled_steps`` is a bitmask that specifies whether decryption,
verity, or both is enabled. After the bio completes, for each needed
postprocessing step the filesystem enqueues the bio_post_read_ctx on a
workqueue, and then the workqueue work does the decryption or
verification. Finally, pages where no decryption or verity error
occurred are marked Uptodate, and the pages are unlocked.
Files on ext4 and f2fs may contain holes. Normally, ``->readpages()``
simply zeroes holes and sets the corresponding pages Uptodate; no bios
are issued. To prevent this case from bypassing fs-verity, these
filesystems use fsverity_verify_page() to verify hole pages.
ext4 and f2fs disable direct I/O on verity files, since otherwise
direct I/O would bypass fs-verity. (They also do the same for
encrypted files.)
Userspace utility
=================
This document focuses on the kernel, but a userspace utility for
fs-verity can be found at:
https://git.kernel.org/pub/scm/linux/kernel/git/ebiggers/fsverity-utils.git
See the README.md file in the fsverity-utils source tree for details,
including examples of setting up fs-verity protected files.
Tests
=====
To test fs-verity, use xfstests. For example, using `kvm-xfstests
<https://github.com/tytso/xfstests-bld/blob/master/Documentation/kvm-quickstart.md>`_::
kvm-xfstests -c ext4,f2fs -g verity
FAQ
===
This section answers frequently asked questions about fs-verity that
weren't already directly answered in other parts of this document.
:Q: Why isn't fs-verity part of IMA?
:A: fs-verity and IMA (Integrity Measurement Architecture) have
different focuses. fs-verity is a filesystem-level mechanism for
hashing individual files using a Merkle tree. In contrast, IMA
specifies a system-wide policy that specifies which files are
hashed and what to do with those hashes, such as log them,
authenticate them, or add them to a measurement list.
IMA is planned to support the fs-verity hashing mechanism as an
alternative to doing full file hashes, for people who want the
performance and security benefits of the Merkle tree based hash.
But it doesn't make sense to force all uses of fs-verity to be
through IMA. As a standalone filesystem feature, fs-verity
already meets many users' needs, and it's testable like other
filesystem features e.g. with xfstests.
:Q: Isn't fs-verity useless because the attacker can just modify the
hashes in the Merkle tree, which is stored on-disk?
:A: To verify the authenticity of an fs-verity file you must verify
the authenticity of the "file measurement", which is basically the
root hash of the Merkle tree. See `Use cases`_.
:Q: Isn't fs-verity useless because the attacker can just replace a
verity file with a non-verity one?
:A: See `Use cases`_. In the initial use case, it's really trusted
userspace code that authenticates the files; fs-verity is just a
tool to do this job efficiently and securely. The trusted
userspace code will consider non-verity files to be inauthentic.
:Q: Why does the Merkle tree need to be stored on-disk? Couldn't you
store just the root hash?
:A: If the Merkle tree wasn't stored on-disk, then you'd have to
compute the entire tree when the file is first accessed, even if
just one byte is being read. This is a fundamental consequence of
how Merkle tree hashing works. To verify a leaf node, you need to
verify the whole path to the root hash, including the root node
(the thing which the root hash is a hash of). But if the root
node isn't stored on-disk, you have to compute it by hashing its
children, and so on until you've actually hashed the entire file.
That defeats most of the point of doing a Merkle tree-based hash,
since if you have to hash the whole file ahead of time anyway,
then you could simply do sha256(file) instead. That would be much
simpler, and a bit faster too.
It's true that an in-memory Merkle tree could still provide the
advantage of verification on every read rather than just on the
first read. However, it would be inefficient because every time a
hash page gets evicted (you can't pin the entire Merkle tree into
memory, since it may be very large), in order to restore it you
again need to hash everything below it in the tree. This again
defeats most of the point of doing a Merkle tree-based hash, since
a single block read could trigger re-hashing gigabytes of data.
:Q: But couldn't you store just the leaf nodes and compute the rest?
:A: See previous answer; this really just moves up one level, since
one could alternatively interpret the data blocks as being the
leaf nodes of the Merkle tree. It's true that the tree can be
computed much faster if the leaf level is stored rather than just
the data, but that's only because each level is less than 1% the
size of the level below (assuming the recommended settings of
SHA-256 and 4K blocks). For the exact same reason, by storing
"just the leaf nodes" you'd already be storing over 99% of the
tree, so you might as well simply store the whole tree.
:Q: Can the Merkle tree be built ahead of time, e.g. distributed as
part of a package that is installed to many computers?
:A: This isn't currently supported. It was part of the original
design, but was removed to simplify the kernel UAPI and because it
wasn't a critical use case. Files are usually installed once and
used many times, and cryptographic hashing is somewhat fast on
most modern processors.
:Q: Why doesn't fs-verity support writes?
:A: Write support would be very difficult and would require a
completely different design, so it's well outside the scope of
fs-verity. Write support would require:
- A way to maintain consistency between the data and hashes,
including all levels of hashes, since corruption after a crash
(especially of potentially the entire file!) is unacceptable.
The main options for solving this are data journalling,
copy-on-write, and log-structured volume. But it's very hard to
retrofit existing filesystems with new consistency mechanisms.
Data journalling is available on ext4, but is very slow.
- Rebuilding the the Merkle tree after every write, which would be
extremely inefficient. Alternatively, a different authenticated
dictionary structure such as an "authenticated skiplist" could
be used. However, this would be far more complex.
Compare it to dm-verity vs. dm-integrity. dm-verity is very
simple: the kernel just verifies read-only data against a
read-only Merkle tree. In contrast, dm-integrity supports writes
but is slow, is much more complex, and doesn't actually support
full-device authentication since it authenticates each sector
independently, i.e. there is no "root hash". It doesn't really
make sense for the same device-mapper target to support these two
very different cases; the same applies to fs-verity.
:Q: Since verity files are immutable, why isn't the immutable bit set?
:A: The existing "immutable" bit (FS_IMMUTABLE_FL) already has a
specific set of semantics which not only make the file contents
read-only, but also prevent the file from being deleted, renamed,
linked to, or having its owner or mode changed. These extra
properties are unwanted for fs-verity, so reusing the immutable
bit isn't appropriate.
:Q: Why does the API use ioctls instead of setxattr() and getxattr()?
:A: Abusing the xattr interface for basically arbitrary syscalls is
heavily frowned upon by most of the Linux filesystem developers.
An xattr should really just be an xattr on-disk, not an API to
e.g. magically trigger construction of a Merkle tree.
:Q: Does fs-verity support remote filesystems?
:A: Only ext4 and f2fs support is implemented currently, but in
principle any filesystem that can store per-file verity metadata
can support fs-verity, regardless of whether it's local or remote.
Some filesystems may have fewer options of where to store the
verity metadata; one possibility is to store it past the end of
the file and "hide" it from userspace by manipulating i_size. The
data verification functions provided by ``fs/verity/`` also assume
that the filesystem uses the Linux pagecache, but both local and
remote filesystems normally do so.
:Q: Why is anything filesystem-specific at all? Shouldn't fs-verity
be implemented entirely at the VFS level?
:A: There are many reasons why this is not possible or would be very
difficult, including the following:
- To prevent bypassing verification, pages must not be marked
Uptodate until they've been verified. Currently, each
filesystem is responsible for marking pages Uptodate via
``->readpages()``. Therefore, currently it's not possible for
the VFS to do the verification on its own. Changing this would
require significant changes to the VFS and all filesystems.
- It would require defining a filesystem-independent way to store
the verity metadata. Extended attributes don't work for this
because (a) the Merkle tree may be gigabytes, but many
filesystems assume that all xattrs fit into a single 4K
filesystem block, and (b) ext4 and f2fs encryption doesn't
encrypt xattrs, yet the Merkle tree *must* be encrypted when the
file contents are, because it stores hashes of the plaintext
file contents.
So the verity metadata would have to be stored in an actual
file. Using a separate file would be very ugly, since the
metadata is fundamentally part of the file to be protected, and
it could cause problems where users could delete the real file
but not the metadata file or vice versa. On the other hand,
having it be in the same file would break applications unless
filesystems' notion of i_size were divorced from the VFS's,
which would be complex and require changes to all filesystems.
- It's desirable that FS_IOC_ENABLE_VERITY uses the filesystem's
transaction mechanism so that either the file ends up with
verity enabled, or no changes were made. Allowing intermediate
states to occur after a crash may cause problems.

1
Documentation/filesystems/index.rst
View file

@ -359,3 +359,4 @@ encryption of files and directories.
:maxdepth: 2
fscrypt
fsverity

13
MAINTAINERS
View file

@ -5999,6 +5999,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/tytso/fscrypt.git
S: Supported
F: fs/crypto/
F: include/linux/fscrypt*.h
F: include/uapi/linux/fscrypt.h
F: Documentation/filesystems/fscrypt.rst
FSI-ATTACHED I2C DRIVER
@ -6017,6 +6018,18 @@ S: Maintained
F: fs/notify/
F: include/linux/fsnotify*.h
FSVERITY: READ-ONLY FILE-BASED AUTHENTICITY PROTECTION
M: Eric Biggers <ebiggers@kernel.org>
M: Theodore Y. Ts'o <tytso@mit.edu>
L: linux-fscrypt@vger.kernel.org
Q: https://patchwork.kernel.org/project/linux-fscrypt/list/
T: git git://git.kernel.org/pub/scm/fs/fscrypt/fscrypt.git fsverity
S: Supported
F: fs/verity/
F: include/linux/fsverity.h
F: include/uapi/linux/fsverity.h
F: Documentation/filesystems/fsverity.rst
FUJITSU LAPTOP EXTRAS
M: Jonathan Woithe <jwoithe@just42.net>
L: platform-driver-x86@vger.kernel.org

1
arch/arm64/configs/gki_defconfig
View file

@ -396,7 +396,6 @@ CONFIG_HARDENED_USERCOPY=y
CONFIG_SECURITY_SELINUX=y
CONFIG_CRYPTO_ADIANTUM=y
CONFIG_CRYPTO_MD4=y
CONFIG_CRYPTO_SHA512=y
CONFIG_CRYPTO_LZ4=y
CONFIG_CRYPTO_ZSTD=y
CONFIG_CRYPTO_ANSI_CPRNG=y

1
arch/x86/configs/gki_defconfig
View file

@ -333,7 +333,6 @@ CONFIG_SECURITY_NETWORK=y
CONFIG_HARDENED_USERCOPY=y
CONFIG_SECURITY_SELINUX=y
CONFIG_CRYPTO_ADIANTUM=y
CONFIG_CRYPTO_SHA512=y
CONFIG_CRYPTO_LZ4=y
CONFIG_CRYPTO_ZSTD=y
CONFIG_CRYPTO_ANSI_CPRNG=y

3
fs/Kconfig
View file

@ -105,6 +105,8 @@ config MANDATORY_FILE_LOCKING
source "fs/crypto/Kconfig"
source "fs/verity/Kconfig"
source "fs/notify/Kconfig"
source "fs/quota/Kconfig"
@ -314,5 +316,6 @@ endif # NETWORK_FILESYSTEMS
source "fs/nls/Kconfig"
source "fs/dlm/Kconfig"
source "fs/unicode/Kconfig"
endmenu

2
fs/Makefile
View file

@ -32,6 +32,7 @@ obj-$(CONFIG_USERFAULTFD) += userfaultfd.o
obj-$(CONFIG_AIO) += aio.o
obj-$(CONFIG_FS_DAX) += dax.o
obj-$(CONFIG_FS_ENCRYPTION) += crypto/
obj-$(CONFIG_FS_VERITY) += verity/
obj-$(CONFIG_FILE_LOCKING) += locks.o
obj-$(CONFIG_COMPAT) += compat.o compat_ioctl.o
obj-$(CONFIG_BINFMT_AOUT) += binfmt_aout.o
@ -91,6 +92,7 @@ obj-$(CONFIG_EXPORTFS) += exportfs/
obj-$(CONFIG_NFSD) += nfsd/
obj-$(CONFIG_LOCKD) += lockd/
obj-$(CONFIG_NLS) += nls/
obj-$(CONFIG_UNICODE) += unicode/
obj-$(CONFIG_SYSV_FS) += sysv/
obj-$(CONFIG_CIFS) += cifs/
obj-$(CONFIG_HPFS_FS) += hpfs/

2
fs/crypto/Kconfig
View file

@ -6,6 +6,8 @@ config FS_ENCRYPTION
select CRYPTO_ECB
select CRYPTO_XTS
select CRYPTO_CTS
select CRYPTO_SHA512
select CRYPTO_HMAC
select KEYS
help
Enable encryption of files and directories. This

10
fs/crypto/Makefile
View file

@ -1,4 +1,12 @@
obj-$(CONFIG_FS_ENCRYPTION) += fscrypto.o
fscrypto-y := crypto.o fname.o hooks.o keyinfo.o policy.o
fscrypto-y := crypto.o \
fname.o \
hkdf.o \
hooks.o \
keyring.o \
keysetup.o \
keysetup_v1.o \
policy.o
fscrypto-$(CONFIG_BLOCK) += bio.o

45
fs/crypto/crypto.c
View file

@ -140,7 +140,7 @@ void fscrypt_generate_iv(union fscrypt_iv *iv, u64 lblk_num,
memset(iv, 0, ci->ci_mode->ivsize);
iv->lblk_num = cpu_to_le64(lblk_num);
if (ci->ci_flags & FS_POLICY_FLAG_DIRECT_KEY)
if (fscrypt_is_direct_key_policy(&ci->ci_policy))
memcpy(iv->nonce, ci->ci_nonce, FS_KEY_DERIVATION_NONCE_SIZE);
if (ci->ci_essiv_tfm != NULL)
@ -187,10 +187,8 @@ int fscrypt_crypt_block(const struct inode *inode, fscrypt_direction_t rw,
res = crypto_wait_req(crypto_skcipher_encrypt(req), &wait);
skcipher_request_free(req);
if (res) {
fscrypt_err(inode->i_sb,
"%scryption failed for inode %lu, block %llu: %d",
(rw == FS_DECRYPT ? "de" : "en"),
inode->i_ino, lblk_num, res);
fscrypt_err(inode, "%scryption failed for block %llu: %d",
(rw == FS_DECRYPT ? "De" : "En"), lblk_num, res);
return res;
}
return 0;
@ -452,7 +450,7 @@ fail:
return res;
}
void fscrypt_msg(struct super_block *sb, const char *level,
void fscrypt_msg(const struct inode *inode, const char *level,
const char *fmt, ...)
{
static DEFINE_RATELIMIT_STATE(rs, DEFAULT_RATELIMIT_INTERVAL,
@ -466,8 +464,9 @@ void fscrypt_msg(struct super_block *sb, const char *level,
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
if (sb)
printk("%sfscrypt (%s): %pV\n", level, sb->s_id, &vaf);
if (inode)
printk("%sfscrypt (%s, inode %lu): %pV\n",
level, inode->i_sb->s_id, inode->i_ino, &vaf);
else
printk("%sfscrypt: %pV\n", level, &vaf);
va_end(args);
@ -478,6 +477,8 @@ void fscrypt_msg(struct super_block *sb, const char *level,
*/
static int __init fscrypt_init(void)
{
int err = -ENOMEM;
/*
* Use an unbound workqueue to allow bios to be decrypted in parallel
* even when they happen to complete on the same CPU. This sacrifices
@ -500,31 +501,19 @@ static int __init fscrypt_init(void)
if (!fscrypt_info_cachep)
goto fail_free_ctx;
err = fscrypt_init_keyring();
if (err)
goto fail_free_info;
return 0;
fail_free_info:
kmem_cache_destroy(fscrypt_info_cachep);
fail_free_ctx:
kmem_cache_destroy(fscrypt_ctx_cachep);
fail_free_queue:
destroy_workqueue(fscrypt_read_workqueue);
fail:
return -ENOMEM;
return err;
}
module_init(fscrypt_init)
/**
* fscrypt_exit() - Shutdown the fs encryption system
*/
static void __exit fscrypt_exit(void)
{
fscrypt_destroy();
if (fscrypt_read_workqueue)
destroy_workqueue(fscrypt_read_workqueue);
kmem_cache_destroy(fscrypt_ctx_cachep);
kmem_cache_destroy(fscrypt_info_cachep);
fscrypt_essiv_cleanup();
}
module_exit(fscrypt_exit);
MODULE_LICENSE("GPL");
late_initcall(fscrypt_init)

47
fs/crypto/fname.c
View file

@ -71,9 +71,7 @@ int fname_encrypt(struct inode *inode, const struct qstr *iname,
res = crypto_wait_req(crypto_skcipher_encrypt(req), &wait);
skcipher_request_free(req);
if (res < 0) {
fscrypt_err(inode->i_sb,
"Filename encryption failed for inode %lu: %d",
inode->i_ino, res);
fscrypt_err(inode, "Filename encryption failed: %d", res);
return res;
}
@ -117,9 +115,7 @@ static int fname_decrypt(struct inode *inode,
res = crypto_wait_req(crypto_skcipher_decrypt(req), &wait);
skcipher_request_free(req);
if (res < 0) {
fscrypt_err(inode->i_sb,
"Filename decryption failed for inode %lu: %d",
inode->i_ino, res);
fscrypt_err(inode, "Filename decryption failed: %d", res);
return res;
}
@ -127,44 +123,45 @@ static int fname_decrypt(struct inode *inode,
return 0;
}
static const char *lookup_table =
static const char lookup_table[65] =
"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+,";
#define BASE64_CHARS(nbytes) DIV_ROUND_UP((nbytes) * 4, 3)
/**
* digest_encode() -
* base64_encode() -
*
* Encodes the input digest using characters from the set [a-zA-Z0-9_+].
* Encodes the input string using characters from the set [A-Za-z0-9+,].
* The encoded string is roughly 4/3 times the size of the input string.
*
* Return: length of the encoded string
*/
static int digest_encode(const char *src, int len, char *dst)
static int base64_encode(const u8 *src, int len, char *dst)
{
int i = 0, bits = 0, ac = 0;
int i, bits = 0, ac = 0;
char *cp = dst;
while (i < len) {
ac += (((unsigned char) src[i]) << bits);
for (i = 0; i < len; i++) {
ac += src[i] << bits;
bits += 8;
do {
*cp++ = lookup_table[ac & 0x3f];
ac >>= 6;
bits -= 6;
} while (bits >= 6);
i++;
}
if (bits)
*cp++ = lookup_table[ac & 0x3f];
return cp - dst;
}
static int digest_decode(const char *src, int len, char *dst)
static int base64_decode(const char *src, int len, u8 *dst)
{
int i = 0, bits = 0, ac = 0;
int i, bits = 0, ac = 0;
const char *p;
char *cp = dst;
u8 *cp = dst;
while (i < len) {
for (i = 0; i < len; i++) {
p = strchr(lookup_table, src[i]);
if (p == NULL || src[i] == 0)
return -2;
@ -175,7 +172,6 @@ static int digest_decode(const char *src, int len, char *dst)
ac >>= 8;
bits -= 8;
}
i++;
}
if (ac)
return -1;
@ -185,8 +181,9 @@ static int digest_decode(const char *src, int len, char *dst)
bool fscrypt_fname_encrypted_size(const struct inode *inode, u32 orig_len,
u32 max_len, u32 *encrypted_len_ret)
{
int padding = 4 << (inode->i_crypt_info->ci_flags &
FS_POLICY_FLAGS_PAD_MASK);
const struct fscrypt_info *ci = inode->i_crypt_info;
int padding = 4 << (fscrypt_policy_flags(&ci->ci_policy) &
FSCRYPT_POLICY_FLAGS_PAD_MASK);
u32 encrypted_len;
if (orig_len > max_len)
@ -272,7 +269,7 @@ int fscrypt_fname_disk_to_usr(struct inode *inode,
return fname_decrypt(inode, iname, oname);
if (iname->len <= FSCRYPT_FNAME_MAX_UNDIGESTED_SIZE) {
oname->len = digest_encode(iname->name, iname->len,
oname->len = base64_encode(iname->name, iname->len,
oname->name);
return 0;
}
@ -287,7 +284,7 @@ int fscrypt_fname_disk_to_usr(struct inode *inode,
FSCRYPT_FNAME_DIGEST(iname->name, iname->len),
FSCRYPT_FNAME_DIGEST_SIZE);
oname->name[0] = '_';
oname->len = 1 + digest_encode((const char *)&digested_name,
oname->len = 1 + base64_encode((const u8 *)&digested_name,
sizeof(digested_name), oname->name + 1);
return 0;
}
@ -380,8 +377,8 @@ int fscrypt_setup_filename(struct inode *dir, const struct qstr *iname,
if (fname->crypto_buf.name == NULL)
return -ENOMEM;
ret = digest_decode(iname->name + digested, iname->len - digested,
fname->crypto_buf.name);
ret = base64_decode(iname->name + digested, iname->len - digested,
fname->crypto_buf.name);
if (ret < 0) {
ret = -ENOENT;
goto errout;

403
fs/crypto/fscrypt_private.h
View file

@ -4,9 +4,8 @@
*
* Copyright (C) 2015, Google, Inc.
*
* This contains encryption key functions.
*
* Written by Michael Halcrow, Ildar Muslukhov, and Uday Savagaonkar, 2015.
* Originally written by Michael Halcrow, Ildar Muslukhov, and Uday Savagaonkar.
* Heavily modified since then.
*/
#ifndef _FSCRYPT_PRIVATE_H
@ -15,30 +14,133 @@
#include <linux/fscrypt.h>
#include <crypto/hash.h>
/* Encryption parameters */
#define CONST_STRLEN(str) (sizeof(str) - 1)
#define FS_KEY_DERIVATION_NONCE_SIZE 16
/**
* Encryption context for inode
*
* Protector format:
* 1 byte: Protector format (1 = this version)
* 1 byte: File contents encryption mode
* 1 byte: File names encryption mode
* 1 byte: Flags
* 8 bytes: Master Key descriptor
* 16 bytes: Encryption Key derivation nonce
*/
struct fscrypt_context {
u8 format;
#define FSCRYPT_MIN_KEY_SIZE 16
#define FSCRYPT_CONTEXT_V1 1
#define FSCRYPT_CONTEXT_V2 2
struct fscrypt_context_v1 {
u8 version; /* FSCRYPT_CONTEXT_V1 */
u8 contents_encryption_mode;
u8 filenames_encryption_mode;
u8 flags;
u8 master_key_descriptor[FS_KEY_DESCRIPTOR_SIZE];
u8 master_key_descriptor[FSCRYPT_KEY_DESCRIPTOR_SIZE];
u8 nonce[FS_KEY_DERIVATION_NONCE_SIZE];
} __packed;
};
#define FS_ENCRYPTION_CONTEXT_FORMAT_V1 1
struct fscrypt_context_v2 {
u8 version; /* FSCRYPT_CONTEXT_V2 */
u8 contents_encryption_mode;
u8 filenames_encryption_mode;
u8 flags;
u8 __reserved[4];
u8 master_key_identifier[FSCRYPT_KEY_IDENTIFIER_SIZE];
u8 nonce[FS_KEY_DERIVATION_NONCE_SIZE];
};
/**
* fscrypt_context - the encryption context of an inode
*
* This is the on-disk equivalent of an fscrypt_policy, stored alongside each
* encrypted file usually in a hidden extended attribute. It contains the
* fields from the fscrypt_policy, in order to identify the encryption algorithm
* and key with which the file is encrypted. It also contains a nonce that was
* randomly generated by fscrypt itself; this is used as KDF input or as a tweak
* to cause different files to be encrypted differently.
*/
union fscrypt_context {
u8 version;
struct fscrypt_context_v1 v1;
struct fscrypt_context_v2 v2;
};
/*
* Return the size expected for the given fscrypt_context based on its version
* number, or 0 if the context version is unrecognized.
*/
static inline int fscrypt_context_size(const union fscrypt_context *ctx)
{
switch (ctx->version) {
case FSCRYPT_CONTEXT_V1:
BUILD_BUG_ON(sizeof(ctx->v1) != 28);
return sizeof(ctx->v1);
case FSCRYPT_CONTEXT_V2:
BUILD_BUG_ON(sizeof(ctx->v2) != 40);
return sizeof(ctx->v2);
}
return 0;
}
#undef fscrypt_policy
union fscrypt_policy {
u8 version;
struct fscrypt_policy_v1 v1;
struct fscrypt_policy_v2 v2;
};
/*
* Return the size expected for the given fscrypt_policy based on its version
* number, or 0 if the policy version is unrecognized.
*/
static inline int fscrypt_policy_size(const union fscrypt_policy *policy)
{
switch (policy->version) {
case FSCRYPT_POLICY_V1:
return sizeof(policy->v1);
case FSCRYPT_POLICY_V2:
return sizeof(policy->v2);
}
return 0;
}
/* Return the contents encryption mode of a valid encryption policy */
static inline u8
fscrypt_policy_contents_mode(const union fscrypt_policy *policy)
{
switch (policy->version) {
case FSCRYPT_POLICY_V1:
return policy->v1.contents_encryption_mode;
case FSCRYPT_POLICY_V2:
return policy->v2.contents_encryption_mode;
}
BUG();
}
/* Return the filenames encryption mode of a valid encryption policy */
static inline u8
fscrypt_policy_fnames_mode(const union fscrypt_policy *policy)
{
switch (policy->version) {
case FSCRYPT_POLICY_V1:
return policy->v1.filenames_encryption_mode;
case FSCRYPT_POLICY_V2:
return policy->v2.filenames_encryption_mode;
}
BUG();
}
/* Return the flags (FSCRYPT_POLICY_FLAG*) of a valid encryption policy */
static inline u8
fscrypt_policy_flags(const union fscrypt_policy *policy)
{
switch (policy->version) {
case FSCRYPT_POLICY_V1:
return policy->v1.flags;
case FSCRYPT_POLICY_V2:
return policy->v2.flags;
}
BUG();
}
static inline bool
fscrypt_is_direct_key_policy(const union fscrypt_policy *policy)
{
return fscrypt_policy_flags(policy) & FSCRYPT_POLICY_FLAG_DIRECT_KEY;
}
/**
* For encrypted symlinks, the ciphertext length is stored at the beginning
@ -68,23 +170,37 @@ struct fscrypt_info {
struct crypto_cipher *ci_essiv_tfm;
/*
* Encryption mode used for this inode. It corresponds to either
* ci_data_mode or ci_filename_mode, depending on the inode type.
* Encryption mode used for this inode. It corresponds to either the
* contents or filenames encryption mode, depending on the inode type.
*/
struct fscrypt_mode *ci_mode;
/*
* If non-NULL, then this inode uses a master key directly rather than a
* derived key, and ci_ctfm will equal ci_master_key->mk_ctfm.
* Otherwise, this inode uses a derived key.
*/
struct fscrypt_master_key *ci_master_key;
/* Back-pointer to the inode */
struct inode *ci_inode;
/* fields from the fscrypt_context */
u8 ci_data_mode;
u8 ci_filename_mode;
u8 ci_flags;
u8 ci_master_key_descriptor[FS_KEY_DESCRIPTOR_SIZE];
/*
* The master key with which this inode was unlocked (decrypted). This
* will be NULL if the master key was found in a process-subscribed
* keyring rather than in the filesystem-level keyring.
*/
struct key *ci_master_key;
/*
* Link in list of inodes that were unlocked with the master key.
* Only used when ->ci_master_key is set.
*/
struct list_head ci_master_key_link;
/*
* If non-NULL, then encryption is done using the master key directly
* and ci_ctfm will equal ci_direct_key->dk_ctfm.
*/
struct fscrypt_direct_key *ci_direct_key;
/* The encryption policy used by this inode */
union fscrypt_policy ci_policy;
/* This inode's nonce, copied from the fscrypt_context */
u8 ci_nonce[FS_KEY_DERIVATION_NONCE_SIZE];
};
@ -98,16 +214,16 @@ typedef enum {
static inline bool fscrypt_valid_enc_modes(u32 contents_mode,
u32 filenames_mode)
{
if (contents_mode == FS_ENCRYPTION_MODE_AES_128_CBC &&
filenames_mode == FS_ENCRYPTION_MODE_AES_128_CTS)
if (contents_mode == FSCRYPT_MODE_AES_128_CBC &&
filenames_mode == FSCRYPT_MODE_AES_128_CTS)
return true;
if (contents_mode == FS_ENCRYPTION_MODE_AES_256_XTS &&
filenames_mode == FS_ENCRYPTION_MODE_AES_256_CTS)
if (contents_mode == FSCRYPT_MODE_AES_256_XTS &&
filenames_mode == FSCRYPT_MODE_AES_256_CTS)
return true;
if (contents_mode == FS_ENCRYPTION_MODE_ADIANTUM &&
filenames_mode == FS_ENCRYPTION_MODE_ADIANTUM)
if (contents_mode == FSCRYPT_MODE_ADIANTUM &&
filenames_mode == FSCRYPT_MODE_ADIANTUM)
return true;
return false;
@ -125,12 +241,12 @@ extern struct page *fscrypt_alloc_bounce_page(gfp_t gfp_flags);
extern const struct dentry_operations fscrypt_d_ops;
extern void __printf(3, 4) __cold
fscrypt_msg(struct super_block *sb, const char *level, const char *fmt, ...);
fscrypt_msg(const struct inode *inode, const char *level, const char *fmt, ...);
#define fscrypt_warn(sb, fmt, ...) \
fscrypt_msg(sb, KERN_WARNING, fmt, ##__VA_ARGS__)
#define fscrypt_err(sb, fmt, ...) \
fscrypt_msg(sb, KERN_ERR, fmt, ##__VA_ARGS__)
#define fscrypt_warn(inode, fmt, ...) \
fscrypt_msg((inode), KERN_WARNING, fmt, ##__VA_ARGS__)
#define fscrypt_err(inode, fmt, ...) \
fscrypt_msg((inode), KERN_ERR, fmt, ##__VA_ARGS__)
#define FSCRYPT_MAX_IV_SIZE 32
@ -155,7 +271,172 @@ extern bool fscrypt_fname_encrypted_size(const struct inode *inode,
u32 orig_len, u32 max_len,
u32 *encrypted_len_ret);
/* keyinfo.c */
/* hkdf.c */
struct fscrypt_hkdf {
struct crypto_shash *hmac_tfm;
};
extern int fscrypt_init_hkdf(struct fscrypt_hkdf *hkdf, const u8 *master_key,
unsigned int master_key_size);
/*
* The list of contexts in which fscrypt uses HKDF. These values are used as
* the first byte of the HKDF application-specific info string to guarantee that
* info strings are never repeated between contexts. This ensures that all HKDF
* outputs are unique and cryptographically isolated, i.e. knowledge of one
* output doesn't reveal another.
*/
#define HKDF_CONTEXT_KEY_IDENTIFIER 1
#define HKDF_CONTEXT_PER_FILE_KEY 2
#define HKDF_CONTEXT_PER_MODE_KEY 3
extern int fscrypt_hkdf_expand(struct fscrypt_hkdf *hkdf, u8 context,
const u8 *info, unsigned int infolen,
u8 *okm, unsigned int okmlen);
extern void fscrypt_destroy_hkdf(struct fscrypt_hkdf *hkdf);
/* keyring.c */
/*
* fscrypt_master_key_secret - secret key material of an in-use master key
*/
struct fscrypt_master_key_secret {
/*
* For v2 policy keys: HKDF context keyed by this master key.
* For v1 policy keys: not set (hkdf.hmac_tfm == NULL).
*/
struct fscrypt_hkdf hkdf;
/* Size of the raw key in bytes. Set even if ->raw isn't set. */
u32 size;
/* For v1 policy keys: the raw key. Wiped for v2 policy keys. */
u8 raw[FSCRYPT_MAX_KEY_SIZE];
} __randomize_layout;
/*
* fscrypt_master_key - an in-use master key
*
* This represents a master encryption key which has been added to the
* filesystem and can be used to "unlock" the encrypted files which were
* encrypted with it.
*/
struct fscrypt_master_key {
/*
* The secret key material. After FS_IOC_REMOVE_ENCRYPTION_KEY is
* executed, this is wiped and no new inodes can be unlocked with this
* key; however, there may still be inodes in ->mk_decrypted_inodes
* which could not be evicted. As long as some inodes still remain,
* FS_IOC_REMOVE_ENCRYPTION_KEY can be retried, or
* FS_IOC_ADD_ENCRYPTION_KEY can add the secret again.
*
* Locking: protected by key->sem (outer) and mk_secret_sem (inner).
* The reason for two locks is that key->sem also protects modifying
* mk_users, which ranks it above the semaphore for the keyring key
* type, which is in turn above page faults (via keyring_read). But
* sometimes filesystems call fscrypt_get_encryption_info() from within
* a transaction, which ranks it below page faults. So we need a
* separate lock which protects mk_secret but not also mk_users.
*/
struct fscrypt_master_key_secret mk_secret;
struct rw_semaphore mk_secret_sem;
/*
* For v1 policy keys: an arbitrary key descriptor which was assigned by
* userspace (->descriptor).
*
* For v2 policy keys: a cryptographic hash of this key (->identifier).
*/
struct fscrypt_key_specifier mk_spec;
/*
* Keyring which contains a key of type 'key_type_fscrypt_user' for each
* user who has added this key. Normally each key will be added by just
* one user, but it's possible that multiple users share a key, and in
* that case we need to keep track of those users so that one user can't
* remove the key before the others want it removed too.
*
* This is NULL for v1 policy keys; those can only be added by root.
*
* Locking: in addition to this keyrings own semaphore, this is
* protected by the master key's key->sem, so we can do atomic
* search+insert. It can also be searched without taking any locks, but
* in that case the returned key may have already been removed.
*/
struct key *mk_users;
/*
* Length of ->mk_decrypted_inodes, plus one if mk_secret is present.
* Once this goes to 0, the master key is removed from ->s_master_keys.
* The 'struct fscrypt_master_key' will continue to live as long as the
* 'struct key' whose payload it is, but we won't let this reference
* count rise again.
*/
refcount_t mk_refcount;
/*
* List of inodes that were unlocked using this key. This allows the
* inodes to be evicted efficiently if the key is removed.
*/
struct list_head mk_decrypted_inodes;
spinlock_t mk_decrypted_inodes_lock;
/* Per-mode tfms for DIRECT_KEY policies, allocated on-demand */
struct crypto_skcipher *mk_mode_keys[__FSCRYPT_MODE_MAX + 1];
} __randomize_layout;
static inline bool
is_master_key_secret_present(const struct fscrypt_master_key_secret *secret)
{
/*
* The READ_ONCE() is only necessary for fscrypt_drop_inode() and
* fscrypt_key_describe(). These run in atomic context, so they can't
* take ->mk_secret_sem and thus 'secret' can change concurrently which
* would be a data race. But they only need to know whether the secret
* *was* present at the time of check, so READ_ONCE() suffices.
*/
return READ_ONCE(secret->size) != 0;
}
static inline const char *master_key_spec_type(
const struct fscrypt_key_specifier *spec)
{
switch (spec->type) {
case FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR:
return "descriptor";
case FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER:
return "identifier";
}
return "[unknown]";
}
static inline int master_key_spec_len(const struct fscrypt_key_specifier *spec)
{
switch (spec->type) {
case FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR:
return FSCRYPT_KEY_DESCRIPTOR_SIZE;
case FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER:
return FSCRYPT_KEY_IDENTIFIER_SIZE;
}
return 0;
}
extern struct key *
fscrypt_find_master_key(struct super_block *sb,
const struct fscrypt_key_specifier *mk_spec);
extern int fscrypt_verify_key_added(struct super_block *sb,
const u8 identifier[FSCRYPT_KEY_IDENTIFIER_SIZE]);
extern int __init fscrypt_init_keyring(void);
/* keysetup.c */
struct fscrypt_mode {
const char *friendly_name;
@ -166,6 +447,36 @@ struct fscrypt_mode {
bool needs_essiv;
};
extern void __exit fscrypt_essiv_cleanup(void);
static inline bool
fscrypt_mode_supports_direct_key(const struct fscrypt_mode *mode)
{
return mode->ivsize >= offsetofend(union fscrypt_iv, nonce);
}
extern struct crypto_skcipher *
fscrypt_allocate_skcipher(struct fscrypt_mode *mode, const u8 *raw_key,
const struct inode *inode);
extern int fscrypt_set_derived_key(struct fscrypt_info *ci,
const u8 *derived_key);
/* keysetup_v1.c */
extern void fscrypt_put_direct_key(struct fscrypt_direct_key *dk);
extern int fscrypt_setup_v1_file_key(struct fscrypt_info *ci,
const u8 *raw_master_key);
extern int fscrypt_setup_v1_file_key_via_subscribed_keyrings(
struct fscrypt_info *ci);
/* policy.c */
extern bool fscrypt_policies_equal(const union fscrypt_policy *policy1,
const union fscrypt_policy *policy2);
extern bool fscrypt_supported_policy(const union fscrypt_policy *policy_u,
const struct inode *inode);
extern int fscrypt_policy_from_context(union fscrypt_policy *policy_u,
const union fscrypt_context *ctx_u,
int ctx_size);
#endif /* _FSCRYPT_PRIVATE_H */

183
fs/crypto/hkdf.c Normal file
View file

@ -0,0 +1,183 @@
// SPDX-License-Identifier: GPL-2.0
/*
* Implementation of HKDF ("HMAC-based Extract-and-Expand Key Derivation
* Function"), aka RFC 5869. See also the original paper (Krawczyk 2010):
* "Cryptographic Extraction and Key Derivation: The HKDF Scheme".
*
* This is used to derive keys from the fscrypt master keys.
*
* Copyright 2019 Google LLC
*/
#include <crypto/hash.h>
#include <crypto/sha.h>
#include "fscrypt_private.h"
/*
* HKDF supports any unkeyed cryptographic hash algorithm, but fscrypt uses
* SHA-512 because it is reasonably secure and efficient; and since it produces
* a 64-byte digest, deriving an AES-256-XTS key preserves all 64 bytes of
* entropy from the master key and requires only one iteration of HKDF-Expand.
*/
#define HKDF_HMAC_ALG "hmac(sha512)"
#define HKDF_HASHLEN SHA512_DIGEST_SIZE
/*
* HKDF consists of two steps:
*
* 1. HKDF-Extract: extract a pseudorandom key of length HKDF_HASHLEN bytes from
* the input keying material and optional salt.
* 2. HKDF-Expand: expand the pseudorandom key into output keying material of
* any length, parameterized by an application-specific info string.
*
* HKDF-Extract can be skipped if the input is already a pseudorandom key of
* length HKDF_HASHLEN bytes. However, cipher modes other than AES-256-XTS take
* shorter keys, and we don't want to force users of those modes to provide
* unnecessarily long master keys. Thus fscrypt still does HKDF-Extract. No
* salt is used, since fscrypt master keys should already be pseudorandom and
* there's no way to persist a random salt per master key from kernel mode.
*/
/* HKDF-Extract (RFC 5869 section 2.2), unsalted */
static int hkdf_extract(struct crypto_shash *hmac_tfm, const u8 *ikm,
unsigned int ikmlen, u8 prk[HKDF_HASHLEN])
{
static const u8 default_salt[HKDF_HASHLEN];
SHASH_DESC_ON_STACK(desc, hmac_tfm);
int err;
err = crypto_shash_setkey(hmac_tfm, default_salt, HKDF_HASHLEN);
if (err)
return err;
desc->tfm = hmac_tfm;
desc->flags = 0;
err = crypto_shash_digest(desc, ikm, ikmlen, prk);
shash_desc_zero(desc);
return err;
}
/*
* Compute HKDF-Extract using the given master key as the input keying material,
* and prepare an HMAC transform object keyed by the resulting pseudorandom key.
*
* Afterwards, the keyed HMAC transform object can be used for HKDF-Expand many
* times without having to recompute HKDF-Extract each time.
*/
int fscrypt_init_hkdf(struct fscrypt_hkdf *hkdf, const u8 *master_key,
unsigned int master_key_size)
{
struct crypto_shash *hmac_tfm;
u8 prk[HKDF_HASHLEN];
int err;
hmac_tfm = crypto_alloc_shash(HKDF_HMAC_ALG, 0, 0);
if (IS_ERR(hmac_tfm)) {
fscrypt_err(NULL, "Error allocating " HKDF_HMAC_ALG ": %ld",
PTR_ERR(hmac_tfm));
return PTR_ERR(hmac_tfm);
}
if (WARN_ON(crypto_shash_digestsize(hmac_tfm) != sizeof(prk))) {
err = -EINVAL;
goto err_free_tfm;
}
err = hkdf_extract(hmac_tfm, master_key, master_key_size, prk);
if (err)
goto err_free_tfm;
err = crypto_shash_setkey(hmac_tfm, prk, sizeof(prk));
if (err)
goto err_free_tfm;
hkdf->hmac_tfm = hmac_tfm;
goto out;
err_free_tfm:
crypto_free_shash(hmac_tfm);
out:
memzero_explicit(prk, sizeof(prk));
return err;
}
/*
* HKDF-Expand (RFC 5869 section 2.3). This expands the pseudorandom key, which
* was already keyed into 'hkdf->hmac_tfm' by fscrypt_init_hkdf(), into 'okmlen'
* bytes of output keying material parameterized by the application-specific
* 'info' of length 'infolen' bytes, prefixed by "fscrypt\0" and the 'context'
* byte. This is thread-safe and may be called by multiple threads in parallel.
*
* ('context' isn't part of the HKDF specification; it's just a prefix fscrypt
* adds to its application-specific info strings to guarantee that it doesn't
* accidentally repeat an info string when using HKDF for different purposes.)
*/
int fscrypt_hkdf_expand(struct fscrypt_hkdf *hkdf, u8 context,
const u8 *info, unsigned int infolen,
u8 *okm, unsigned int okmlen)
{
SHASH_DESC_ON_STACK(desc, hkdf->hmac_tfm);
u8 prefix[9];
unsigned int i;
int err;
const u8 *prev = NULL;
u8 counter = 1;
u8 tmp[HKDF_HASHLEN];
if (WARN_ON(okmlen > 255 * HKDF_HASHLEN))
return -EINVAL;
desc->tfm = hkdf->hmac_tfm;
desc->flags = 0;
memcpy(prefix, "fscrypt\0", 8);
prefix[8] = context;
for (i = 0; i < okmlen; i += HKDF_HASHLEN) {
err = crypto_shash_init(desc);
if (err)
goto out;
if (prev) {
err = crypto_shash_update(desc, prev, HKDF_HASHLEN);
if (err)
goto out;
}
err = crypto_shash_update(desc, prefix, sizeof(prefix));
if (err)
goto out;
err = crypto_shash_update(desc, info, infolen);
if (err)
goto out;
BUILD_BUG_ON(sizeof(counter) != 1);
if (okmlen - i < HKDF_HASHLEN) {
err = crypto_shash_finup(desc, &counter, 1, tmp);
if (err)
goto out;
memcpy(&okm[i], tmp, okmlen - i);
memzero_explicit(tmp, sizeof(tmp));
} else {
err = crypto_shash_finup(desc, &counter, 1, &okm[i]);
if (err)
goto out;
}
counter++;
prev = &okm[i];
}
err = 0;
out:
if (unlikely(err))
memzero_explicit(okm, okmlen); /* so caller doesn't need to */
shash_desc_zero(desc);
return err;
}
void fscrypt_destroy_hkdf(struct fscrypt_hkdf *hkdf)
{
crypto_free_shash(hkdf->hmac_tfm);
}

6
fs/crypto/hooks.c
View file

@ -38,9 +38,9 @@ int fscrypt_file_open(struct inode *inode, struct file *filp)
dir = dget_parent(file_dentry(filp));
if (IS_ENCRYPTED(d_inode(dir)) &&
!fscrypt_has_permitted_context(d_inode(dir), inode)) {
fscrypt_warn(inode->i_sb,
"inconsistent encryption contexts: %lu/%lu",
d_inode(dir)->i_ino, inode->i_ino);
fscrypt_warn(inode,
"Inconsistent encryption context (parent directory: %lu)",
d_inode(dir)->i_ino);
err = -EPERM;
}
dput(dir);

Some files were not shown because too many files have changed in this diff Show more